mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Merge branch 'kovidgoyal/master'
This commit is contained in:
Charles Haley
commit
726ff97098
@ -34,6 +34,10 @@ License: LGPL-2.1
|
||||
The full text of the LGPL is distributed as in
|
||||
/usr/share/common-licenses/LGPL-2.1 on Debian systems.
|
||||
|
||||
Files: srx/regex/*
|
||||
Copyright: Matthew Barnett
|
||||
License: Python Software Foundation License
|
||||
|
||||
Files: src/calibre/ebooks/hyphenate.py
|
||||
Copyright: Copyright (C) 1990, 2004, 2005 Gerard D.C. Kuiken.
|
||||
License: other
|
||||
|
||||
@ -1,37 +1,43 @@
|
||||
# vim:fileencoding=utf-8
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
__copyright__ = '2009-2013, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
elmundo.es
|
||||
'''
|
||||
import re
|
||||
import time
|
||||
from calibre.ptempfile import PersistentTemporaryFile
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class ElMundo(BasicNewsRecipe):
|
||||
title = 'El Mundo'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Lider de informacion en espaniol'
|
||||
publisher = 'Unidad Editorial Informacion General S.L.U.'
|
||||
category = 'news, politics, Spain'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'iso8859_15'
|
||||
remove_javascript = True
|
||||
remove_empty_feeds = True
|
||||
language = 'es'
|
||||
masthead_url = 'http://estaticos03.elmundo.es/elmundo/iconos/v4.x/v4.01/bg_h1.png'
|
||||
publication_type = 'newspaper'
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif}
|
||||
.metadata_noticia{font-size: small}
|
||||
.pestana_GDP{font-size: small; font-weight:bold}
|
||||
h1,h2,h3,h4,h5,h6,.subtitulo {color: #3F5974}
|
||||
.hora{color: red}
|
||||
.update{color: gray}
|
||||
"""
|
||||
title = 'El Mundo'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = u'Lider de informacion en español'
|
||||
publisher = 'Unidad Editorial Informacion General S.L.U.'
|
||||
category = 'news, politics, Spain'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'iso8859_15'
|
||||
remove_javascript = True
|
||||
remove_empty_feeds = True
|
||||
language = 'es'
|
||||
ignore_duplicate_articles = {'url'}
|
||||
masthead_url = 'http://estaticos03.elmundo.es/assets/desktop/master/img/iconos/elmundo-portada.png'
|
||||
publication_type = 'newspaper'
|
||||
articles_are_obfuscated = True
|
||||
temp_files = []
|
||||
needs_subscription = 'optional'
|
||||
LOGIN = 'https://seguro.elmundo.es/registro/login.html'
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif}
|
||||
.metadata_noticia{font-size: small}
|
||||
.pestana_GDP{font-size: small; font-weight:bold}
|
||||
h1 {color: #333333; font-family: Georgia,"Times New Roman",Times,serif}
|
||||
.hora{color: red}
|
||||
.update{color: gray}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comments' : description
|
||||
@ -40,86 +46,96 @@ class ElMundo(BasicNewsRecipe):
|
||||
,'publisher' : publisher
|
||||
}
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'noticia'})]
|
||||
remove_tags_before = dict(attrs={'class':['titular','antetitulo'] })
|
||||
remove_tags_before = dict(attrs={'class':['titular','antetitulo','entrada']})
|
||||
remove_tags_after = dict(name='div' , attrs={'id':['desarrollo_noticia','tamano']})
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':'comentarios'}),
|
||||
dict(name=['meta', 'link', 'iframe', 'object'])
|
||||
]
|
||||
remove_attributes = ['lang','border']
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':['herramientas','publicidad_google','comenta','col col-2b','apoyos','no-te-pierdas']})
|
||||
,dict(name='div', attrs={'class':['publicidad publicidad_cuerpo_noticia','comentarios_nav','mensaje_privado','interact']})
|
||||
,dict(name='div', attrs={'class':['num_comentarios estirar']})
|
||||
,dict(name='span', attrs={'class':['links_comentar']})
|
||||
,dict(name='div', attrs={'id':['comentar']})
|
||||
,dict(name='ul', attrs={'class':'herramientas' })
|
||||
,dict(name=['object','link','embed','iframe','base','meta'])
|
||||
]
|
||||
|
||||
def get_browser(self):
|
||||
br = BasicNewsRecipe.get_browser(self)
|
||||
if self.username is not None and self.password is not None:
|
||||
br.open(self.LOGIN)
|
||||
br.select_form(name='login')
|
||||
br['nick' ] = self.username
|
||||
br['clave'] = self.password
|
||||
br.submit()
|
||||
return br
|
||||
|
||||
feeds = [
|
||||
(u'Portada' , u'http://estaticos.elmundo.es/elmundo/rss/portada.xml' )
|
||||
,(u'Deportes' , u'http://estaticos.elmundo.es/elmundodeporte/rss/portada.xml')
|
||||
,(u'Econom\xeda' , u'http://estaticos.elmundo.es/elmundo/rss/economia.xml' )
|
||||
,(u'Espa\xf1a' , u'http://estaticos.elmundo.es/elmundo/rss/espana.xml' )
|
||||
,(u'Internacional' , u'http://estaticos.elmundo.es/elmundo/rss/internacional.xml' )
|
||||
,(u'Cultura' , u'http://estaticos.elmundo.es/elmundo/rss/cultura.xml' )
|
||||
,(u'Ciencia/Ecolog\xeda', u'http://estaticos.elmundo.es/elmundo/rss/ciencia.xml' )
|
||||
,(u'Comunicaci\xf3n' , u'http://estaticos.elmundo.es/elmundo/rss/comunicacion.xml' )
|
||||
,(u'Televisi\xf3n' , u'http://estaticos.elmundo.es/elmundo/rss/television.xml' )
|
||||
(u'Portada' , u'http://elmundo.feedsportal.com/elmundo/rss/portada.xml' )
|
||||
,(u'Deportes' , u'http://elmundo.feedsportal.com/elmundodeporte/rss/portada.xml')
|
||||
,(u'Econom\xeda' , u'http://elmundo.feedsportal.com/elmundo/rss/economia.xml' )
|
||||
,(u'Espa\xf1a' , u'http://elmundo.feedsportal.com/elmundo/rss/espana.xml' )
|
||||
,(u'Internacional' , u'http://elmundo.feedsportal.com/elmundo/rss/internacional.xml' )
|
||||
,(u'Cultura' , u'http://elmundo.feedsportal.com/elmundo/rss/internacional.xml' )
|
||||
,(u'Ciencia/Ecolog\xeda', u'http://elmundo.feedsportal.com/elmundo/rss/ciencia.xml' )
|
||||
,(u'Comunicaci\xf3n' , u'http://elmundo.feedsportal.com/elmundo/rss/comunicacion.xml' )
|
||||
,(u'Televisi\xf3n' , u'http://elmundo.feedsportal.com/elmundo/rss/television.xml' )
|
||||
|
||||
,(u'Salud' , u'http://estaticos.elmundo.es/elmundosalud/rss/portada.xml' )
|
||||
,(u'Solidaridad' , u'http://estaticos.elmundo.es/elmundo/rss/solidaridad.xml' )
|
||||
,(u'Su vivienda' , u'http://estaticos.elmundo.es/elmundo/rss/suvivienda.xml' )
|
||||
,(u'Motor' , u'http://estaticos.elmundo.es/elmundomotor/rss/portada.xml' )
|
||||
,(u'Salud' , u'http://elmundo.feedsportal.com/elmundosalud/rss/portada.xml' )
|
||||
,(u'Solidaridad' , u'http://elmundo.feedsportal.com/elmundo/rss/solidaridad.xml' )
|
||||
,(u'Su vivienda' , u'http://elmundo.feedsportal.com/elmundo/rss/suvivienda.xml' )
|
||||
,(u'Motor' , u'http://elmundo.feedsportal.com/elmundodeporte/rss/motor.xml' )
|
||||
|
||||
,(u'Madrid' , u'http://estaticos.elmundo.es/elmundo/rss/madrid.xml' )
|
||||
,(u'Barcelona' , u'http://estaticos.elmundo.es/elmundo/rss/barcelona.xml' )
|
||||
,(u'Pa\xeds Vasco' , u'http://estaticos.elmundo.es/elmundo/rss/paisvasco.xml' )
|
||||
,(u'Baleares' , u'http://estaticos.elmundo.es/elmundo/rss/baleares.xml' )
|
||||
,(u'Castilla y Le\xf3n' , u'http://estaticos.elmundo.es/elmundo/rss/castillayleon.xml' )
|
||||
,(u'Valladolid' , u'http://estaticos.elmundo.es/elmundo/rss/valladolid.xml' )
|
||||
,(u'Valencia' , u'http://estaticos.elmundo.es/elmundo/rss/valencia.xml' )
|
||||
,(u'Alicante' , u'http://estaticos.elmundo.es/elmundo/rss/alicante.xml' )
|
||||
,(u'Castell\xf3n' , u'http://estaticos.elmundo.es/elmundo/rss/castellon.xml' )
|
||||
,(u'Andaluc\xeda' , u'http://estaticos.elmundo.es/elmundo/rss/andalucia.xml' )
|
||||
,(u'Sevilla' , u'http://estaticos.elmundo.es/elmundo/rss/andalucia_sevilla.xml' )
|
||||
,(u'M\xe1laga' , u'http://estaticos.elmundo.es/elmundo/rss/andalucia_malaga.xml' )
|
||||
,(u'Madrid' , u'http://elmundo.feedsportal.com/elmundo/rss/madrid.xml' )
|
||||
,(u'Barcelona' , u'http://elmundo.feedsportal.com/elmundo/rss/barcelona.xml' )
|
||||
,(u'Pa\xeds Vasco' , u'http://elmundo.feedsportal.com/elmundo/rss/paisvasco.xml' )
|
||||
,(u'Baleares' , u'http://elmundo.feedsportal.com/elmundo/rss/baleares.xml' )
|
||||
,(u'Castilla y Le\xf3n' , u'http://elmundo.feedsportal.com/elmundo/rss/castillayleon.xml' )
|
||||
,(u'Valladolid' , u'http://elmundo.feedsportal.com/elmundo/rss/valladolid.xml' )
|
||||
,(u'Valencia' , u'http://elmundo.feedsportal.com/elmundo/rss/valencia.xml' )
|
||||
,(u'Alicante' , u'http://elmundo.feedsportal.com/elmundo/rss/alicante.xml' )
|
||||
,(u'Castell\xf3n' , u'http://elmundo.feedsportal.com/elmundo/rss/castellon.xml' )
|
||||
,(u'Andaluc\xeda' , u'http://elmundo.feedsportal.com/elmundo/rss/andalucia.xml' )
|
||||
,(u'Sevilla' , u'http://elmundo.feedsportal.com/elmundo/rss/andalucia_sevilla.xml' )
|
||||
,(u'M\xe1laga' , u'http://elmundo.feedsportal.com/elmundo/rss/andalucia_malaga.xml' )
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return soup
|
||||
|
||||
def get_article_url(self, article):
|
||||
return article.get('guid', None)
|
||||
|
||||
|
||||
preprocess_regexps = [
|
||||
# Para presentar la imagen de los videos incrustados
|
||||
|
||||
(re.compile(r'var imagen', re.DOTALL|re.IGNORECASE), lambda match: '--></script><img src'),
|
||||
(re.compile(r'.jpg";', re.DOTALL|re.IGNORECASE), lambda match: '.jpg">'),
|
||||
(re.compile(r'var video=', re.DOTALL|re.IGNORECASE), lambda match: '<script language="Javascript" type="text/javascript"><!--'),
|
||||
|
||||
# Para que no salga la numeración de comentarios: 1, 2, 3 ...
|
||||
|
||||
(re.compile(r'<ol>\n<li style="z-index:', re.DOTALL|re.IGNORECASE), lambda match: '<ul><li style="z-index:'),
|
||||
(re.compile(r'</ol>\n<div class="num_comentarios estirar">', re.DOTALL|re.IGNORECASE), lambda match: '</ul><div class="num_comentarios estirar">'),
|
||||
]
|
||||
realurl = article.get('guid', None)
|
||||
if '/album/' in realurl or '/envivos/' in realurl:
|
||||
return None
|
||||
return realurl
|
||||
|
||||
# Obtener la imagen de portada
|
||||
|
||||
def get_cover_url(self):
|
||||
cover = None
|
||||
cover = self.masthead_url
|
||||
st = time.localtime()
|
||||
year = str(st.tm_year)
|
||||
month = "%.2d" % st.tm_mon
|
||||
day = "%.2d" % st.tm_mday
|
||||
#http://img.kiosko.net/2011/11/19/es/elmundo.750.jpg
|
||||
cover='http://img.kiosko.net/'+ year + '/' + month + '/' + day +'/es/elmundo.750.jpg'
|
||||
br = BasicNewsRecipe.get_browser(self)
|
||||
try:
|
||||
br.open(cover)
|
||||
self.browser.open(cover)
|
||||
except:
|
||||
self.log("\nPortada no disponible")
|
||||
cover ='http://estaticos03.elmundo.es/elmundo/iconos/v4.x/v4.01/bg_h1.png'
|
||||
return cover
|
||||
|
||||
def get_obfuscated_article(self, url):
|
||||
count = 0
|
||||
tries = 5
|
||||
html = None
|
||||
while (count < tries):
|
||||
try:
|
||||
response = self.browser.open(url)
|
||||
html = response.read()
|
||||
count = tries
|
||||
except:
|
||||
print "Retrying download..."
|
||||
count += 1
|
||||
if html is not None:
|
||||
tfile = PersistentTemporaryFile('_fa.html')
|
||||
tfile.write(html)
|
||||
tfile.close()
|
||||
self.temp_files.append(tfile)
|
||||
return tfile.name
|
||||
return None
|
||||
|
||||
def image_url_processor(self, baseurl, url):
|
||||
if url.startswith('//'):
|
||||
return 'http:' + url
|
||||
return url
|
||||
|
||||
|
||||
@ -6,12 +6,16 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
||||
spiegel.de
|
||||
'''
|
||||
|
||||
import time, re
|
||||
from contextlib import closing
|
||||
from calibre import as_unicode
|
||||
from calibre.web.feeds import feed_from_xml, Feed
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Spiegel_ger(BasicNewsRecipe):
|
||||
title = 'Spiegel Online - German'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = "Immer die neueste Meldung auf dem Schirm, sekundenaktuell und uebersichtlich: Mit dem RSS-Angebot von SPIEGEL ONLINE entgeht Ihnen keine wichtige Meldung mehr, selbst wenn Sie keinen Internet-Browser geoeffnet haben. Sie koennen unsere Nachrichten-Feeds ganz einfach abonnieren - unkompliziert, kostenlos und nach Ihren persoenlichen Themen-Vorlieben."
|
||||
description = "Immer die neueste Meldung auf dem Schirm, sekundenaktuell und uebersichtlich: Mit dem RSS-Angebot von SPIEGEL ONLINE entgeht Ihnen keine wichtige Meldung mehr, selbst wenn Sie keinen Internet-Browser geoeffnet haben. Sie koennen unsere Nachrichten-Feeds ganz einfach abonnieren - unkompliziert, kostenlos und nach Ihren persoenlichen Themen-Vorlieben." # noqa
|
||||
publisher = 'SPIEGEL ONLINE Gmbh'
|
||||
category = 'SPIEGEL ONLINE, DER SPIEGEL, Nachrichten, News,Dienste, RSS, RSS, Feedreader, Newsfeed, iGoogle, Netvibes, Widget'
|
||||
oldest_article = 7
|
||||
@ -20,9 +24,18 @@ class Spiegel_ger(BasicNewsRecipe):
|
||||
lang = 'de-DE'
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
auto_cleanup = True
|
||||
auto_cleanup_keep = '//*[@id="spArticleTopAsset"]'
|
||||
encoding = 'cp1252'
|
||||
keep_only_tags = [
|
||||
dict(name='h2', attrs={'class':'article-title'}),
|
||||
dict(id=['js-article-top-wide-asset', 'js-article-column']),
|
||||
]
|
||||
remove_tags = [
|
||||
dict(attrs={'class':lambda x: x and 'asset-html-box' in x.split()}),
|
||||
dict(attrs={'class':lambda x: x and 'article-social-bookmark' in x.split()}),
|
||||
dict(attrs={'class':lambda x: x and 'article-newsfeed-box' in x.split()}),
|
||||
dict(attrs={'class':lambda x: x and 'article-comments-box' in x.split()}),
|
||||
dict(attrs={'class':lambda x: x and 'article-functions-bottom' in x.split()}),
|
||||
]
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
@ -31,10 +44,42 @@ class Spiegel_ger(BasicNewsRecipe):
|
||||
, 'language' : lang
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
feeds = [(u'Spiegel Online', u'http://www.spiegel.de/schlagzeilen/index.rss')]
|
||||
|
||||
def get_article_url(self, *args):
|
||||
url = BasicNewsRecipe.get_article_url(self, *args).replace('#', '/#')
|
||||
ai = re.search(r'ai=(\d+)', url).group(1)
|
||||
soup = self.index_to_soup(url)
|
||||
a = soup.find('a', href=lambda x: x and ai in x)
|
||||
return 'http://www.spiegel.de' + a['href']
|
||||
|
||||
def parse_feeds(self):
|
||||
title, url = self.feeds[0]
|
||||
self.report_progress(0, _('Fetching feed')+' %s...'%(title if title else url))
|
||||
parsed_feeds = []
|
||||
try:
|
||||
with closing(self.browser.open(url)) as s:
|
||||
raw = s.read()
|
||||
raw = raw.replace(b'<guid>http://www.spiegel.de</guid>', b'')
|
||||
|
||||
parsed_feeds.append(feed_from_xml(raw, title=title, log=self.log, oldest_article=self.oldest_article,
|
||||
max_articles_per_feed=self.max_articles_per_feed,
|
||||
get_article_url=self.get_article_url))
|
||||
if (self.delay > 0):
|
||||
time.sleep(self.delay)
|
||||
except Exception as err:
|
||||
feed = Feed()
|
||||
msg = 'Failed feed: %s'%(title if title else url)
|
||||
feed.populate_from_preparsed_feed(msg, [])
|
||||
feed.description = as_unicode(err)
|
||||
parsed_feeds.append(feed)
|
||||
self.log.exception(msg)
|
||||
|
||||
remove = [f for f in parsed_feeds if len(f) == 0 and
|
||||
self.remove_empty_feeds]
|
||||
for f in remove:
|
||||
parsed_feeds.remove(f)
|
||||
|
||||
return parsed_feeds
|
||||
|
||||
|
||||
|
||||
@ -13,7 +13,8 @@ iswindows = re.search('win(32|64)', sys.platform)
|
||||
isosx = 'darwin' in sys.platform
|
||||
isfreebsd = 'freebsd' in sys.platform
|
||||
isnetbsd = 'netbsd' in sys.platform
|
||||
isbsd = isnetbsd or isfreebsd
|
||||
isdragonflybsd = 'dragonfly' in sys.platform
|
||||
isbsd = isnetbsd or isfreebsd or isdragonflybsd
|
||||
islinux = not isosx and not iswindows and not isbsd
|
||||
SRC = os.path.abspath('src')
|
||||
sys.path.insert(0, SRC)
|
||||
|
||||
@ -30,7 +30,6 @@ class Extension(object):
|
||||
return list(set([x if os.path.isabs(x) else os.path.join(SRC, x.replace('/',
|
||||
os.sep)) for x in paths]))
|
||||
|
||||
|
||||
def __init__(self, name, sources, **kwargs):
|
||||
self.name = name
|
||||
self.needs_cxx = bool([1 for x in sources if os.path.splitext(x)[1] in
|
||||
@ -67,10 +66,15 @@ if iswindows:
|
||||
icu_libs = ['icudt', 'icuin', 'icuuc', 'icuio']
|
||||
if isosx:
|
||||
icu_libs = ['icucore']
|
||||
icu_cflags = ['-DU_DISABLE_RENAMING'] # Needed to use system libicucore.dylib
|
||||
icu_cflags = ['-DU_DISABLE_RENAMING'] # Needed to use system libicucore.dylib
|
||||
|
||||
extensions = [
|
||||
|
||||
Extension('_regex',
|
||||
['regex/_regex.c', 'regex/_regex_unicode.c'],
|
||||
headers=['regex/_regex.h']
|
||||
),
|
||||
|
||||
Extension('speedup',
|
||||
['calibre/utils/speedup.c'],
|
||||
),
|
||||
@ -127,7 +131,7 @@ extensions = [
|
||||
|
||||
Extension('freetype',
|
||||
['calibre/utils/fonts/freetype.cpp'],
|
||||
inc_dirs = ft_inc_dirs,
|
||||
inc_dirs=ft_inc_dirs,
|
||||
libraries=ft_libs,
|
||||
lib_dirs=ft_lib_dirs),
|
||||
|
||||
@ -171,23 +175,23 @@ extensions = [
|
||||
|
||||
Extension('pictureflow',
|
||||
['calibre/gui2/pictureflow/pictureflow.cpp'],
|
||||
inc_dirs = ['calibre/gui2/pictureflow'],
|
||||
headers = ['calibre/gui2/pictureflow/pictureflow.h'],
|
||||
sip_files = ['calibre/gui2/pictureflow/pictureflow.sip']
|
||||
inc_dirs=['calibre/gui2/pictureflow'],
|
||||
headers=['calibre/gui2/pictureflow/pictureflow.h'],
|
||||
sip_files=['calibre/gui2/pictureflow/pictureflow.sip']
|
||||
),
|
||||
|
||||
Extension('progress_indicator',
|
||||
['calibre/gui2/progress_indicator/QProgressIndicator.cpp'],
|
||||
inc_dirs = ['calibre/gui2/progress_indicator'],
|
||||
headers = ['calibre/gui2/progress_indicator/QProgressIndicator.h'],
|
||||
sip_files = ['calibre/gui2/progress_indicator/QProgressIndicator.sip']
|
||||
inc_dirs=['calibre/gui2/progress_indicator'],
|
||||
headers=['calibre/gui2/progress_indicator/QProgressIndicator.h'],
|
||||
sip_files=['calibre/gui2/progress_indicator/QProgressIndicator.sip']
|
||||
),
|
||||
|
||||
Extension('qt_hack',
|
||||
['calibre/ebooks/pdf/render/qt_hack.cpp'],
|
||||
inc_dirs = qt_private_inc + ['calibre/ebooks/pdf/render', 'qt-harfbuzz/src'],
|
||||
headers = ['calibre/ebooks/pdf/render/qt_hack.h'],
|
||||
sip_files = ['calibre/ebooks/pdf/render/qt_hack.sip']
|
||||
inc_dirs=qt_private_inc + ['calibre/ebooks/pdf/render', 'qt-harfbuzz/src'],
|
||||
headers=['calibre/ebooks/pdf/render/qt_hack.h'],
|
||||
sip_files=['calibre/ebooks/pdf/render/qt_hack.sip']
|
||||
),
|
||||
|
||||
Extension('unrar',
|
||||
@ -200,7 +204,7 @@ extensions = [
|
||||
volume.o list.o find.o unpack.o cmddata.o filestr.o scantree.o
|
||||
'''.split()] + ['calibre/utils/unrar.cpp'],
|
||||
inc_dirs=['unrar'],
|
||||
cflags = [('/' if iswindows else '-') + x for x in (
|
||||
cflags=[('/' if iswindows else '-') + x for x in (
|
||||
'DSILENT', 'DRARDLL', 'DUNRAR')] + (
|
||||
[] if iswindows else ['-D_FILE_OFFSET_BITS=64',
|
||||
'-D_LARGEFILE_SOURCE']),
|
||||
@ -436,9 +440,9 @@ class Build(Command):
|
||||
if iswindows:
|
||||
#manifest = dest+'.manifest'
|
||||
#cmd = [MT, '-manifest', manifest, '-outputresource:%s;2'%dest]
|
||||
#self.info(*cmd)
|
||||
#self.check_call(cmd)
|
||||
#os.remove(manifest)
|
||||
# self.info(*cmd)
|
||||
# self.check_call(cmd)
|
||||
# os.remove(manifest)
|
||||
for x in ('.exp', '.lib'):
|
||||
x = os.path.splitext(dest)[0]+x
|
||||
if os.path.exists(x):
|
||||
@ -487,7 +491,7 @@ class Build(Command):
|
||||
"style/windowmanager.cpp",
|
||||
]
|
||||
if not iswindows and not isosx:
|
||||
headers.append( "style/shadowhelper.h")
|
||||
headers.append("style/shadowhelper.h")
|
||||
sources.append('style/shadowhelper.cpp')
|
||||
|
||||
pro = textwrap.dedent('''
|
||||
@ -586,7 +590,7 @@ class Build(Command):
|
||||
sbf = self.j(src_dir, self.b(sipf)+'.sbf')
|
||||
if self.newer(sbf, [sipf]+ext.headers):
|
||||
exe = '.exe' if iswindows else ''
|
||||
cmd = [pyqt.sip_bin+exe, '-w', '-c', src_dir, '-b', sbf, '-I'+\
|
||||
cmd = [pyqt.sip_bin+exe, '-w', '-c', src_dir, '-b', sbf, '-I'+
|
||||
pyqt.pyqt_sip_dir] + shlex.split(pyqt.pyqt_sip_flags) + [sipf]
|
||||
self.info(' '.join(cmd))
|
||||
self.check_call(cmd)
|
||||
|
||||
@ -386,8 +386,13 @@ class LinuxFreeze(Command):
|
||||
mod = __import__(sys.calibre_module, fromlist=[1])
|
||||
func = getattr(mod, sys.calibre_function)
|
||||
return func()
|
||||
except SystemExit:
|
||||
raise
|
||||
except SystemExit as err:
|
||||
if err.code is None:
|
||||
return 0
|
||||
if isinstance(err.code, int):
|
||||
return err.code
|
||||
print (err.code)
|
||||
return 1
|
||||
except:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
|
||||
@ -139,6 +139,7 @@ class Plugins(collections.Mapping):
|
||||
'woff',
|
||||
'unrar',
|
||||
'qt_hack',
|
||||
'_regex'
|
||||
]
|
||||
if iswindows:
|
||||
plugins.extend(['winutil', 'wpd', 'winfonts'])
|
||||
|
||||
@ -62,6 +62,12 @@ Everything after the -- is passed to the script.
|
||||
help='Inspect the MOBI file(s) at the specified path(s)')
|
||||
parser.add_option('-t', '--tweak-book', action='store_true',
|
||||
help='Launch the calibre Tweak Book tool in debug mode.')
|
||||
parser.add_option('-x', '--explode-book', default=None,
|
||||
help='Explode the book (exports the book as a collection of HTML '
|
||||
'files and metadata, which you can edit using standard HTML '
|
||||
'editing tools, and then rebuilds the file from the edited HTML. '
|
||||
'Makes no additional changes to the HTML, unlike a full calibre '
|
||||
'conversion).')
|
||||
parser.add_option('-s', '--shutdown-running-calibre', default=False,
|
||||
action='store_true',
|
||||
help=_('Cause a running calibre instance, if any, to be'
|
||||
@ -247,6 +253,9 @@ def main(args=sys.argv):
|
||||
elif opts.tweak_book:
|
||||
from calibre.gui2.tweak_book.main import main
|
||||
main(['ebook-tweak'] + args[1:])
|
||||
elif opts.explode_book:
|
||||
from calibre.ebooks.tweak import tweak
|
||||
tweak(opts.explode_book)
|
||||
elif opts.test_build:
|
||||
from calibre.test_build import test
|
||||
test()
|
||||
|
||||
@ -601,7 +601,7 @@ class libiMobileDevice():
|
||||
error = self.lib.afc_remove_path(byref(self.afc), str(path))
|
||||
|
||||
if error:
|
||||
self._log(" ERROR: %s" % self._afc_error(error))
|
||||
self._log_error(" ERROR: %s path:%s" % (self._afc_error(error), repr(path)))
|
||||
|
||||
def stat(self, path):
|
||||
'''
|
||||
@ -650,7 +650,7 @@ class libiMobileDevice():
|
||||
|
||||
error = self.lib.afc_client_free(byref(self.afc)) & 0xFFFF
|
||||
if error:
|
||||
self._log(" ERROR: %s" % self._afc_error(error))
|
||||
self._log_error(" ERROR: %s" % self._afc_error(error))
|
||||
|
||||
def _afc_client_new(self):
|
||||
'''
|
||||
@ -810,7 +810,7 @@ class libiMobileDevice():
|
||||
error = self.lib.afc_file_close(byref(self.afc),
|
||||
handle) & 0xFFFF
|
||||
if error:
|
||||
self._log(" ERROR: %s" % self._afc_error(error))
|
||||
self._log_error(" ERROR: %s handle:%s" % (self._afc_error(error), handle))
|
||||
|
||||
def _afc_file_open(self, filename, mode='r'):
|
||||
'''
|
||||
@ -850,7 +850,7 @@ class libiMobileDevice():
|
||||
byref(handle)) & 0xFFFF
|
||||
|
||||
if error:
|
||||
self._log(" ERROR: %s" % self._afc_error(error))
|
||||
self._log_error(" ERROR: %s filename:%s" % (self._afc_error(error), repr(filename)))
|
||||
return None
|
||||
else:
|
||||
return handle
|
||||
@ -887,13 +887,13 @@ class libiMobileDevice():
|
||||
size,
|
||||
byref(bytes_read)) & 0xFFFF
|
||||
if error:
|
||||
self._log(" ERROR: %s" % self._afc_error(error))
|
||||
self._log_error(" ERROR: %s handle:%s" % (self._afc_error(error), handle))
|
||||
return data
|
||||
else:
|
||||
data = create_string_buffer(size)
|
||||
error = self.lib.afc_file_read(byref(self.afc), handle, byref(data), size, byref(bytes_read))
|
||||
if error:
|
||||
self._log(" ERROR: %s" % self._afc_error(error))
|
||||
self._log_error(" ERROR: %s handle:%s" % (self._afc_error(error), handle))
|
||||
return data.value
|
||||
|
||||
def _afc_file_write(self, handle, content, mode='w'):
|
||||
@ -933,7 +933,7 @@ class libiMobileDevice():
|
||||
len(content),
|
||||
byref(bytes_written)) & 0xFFFF
|
||||
if error:
|
||||
self._log(" ERROR: %s" % self._afc_error(error))
|
||||
self._log_error(" ERROR: %s handle:%s" % (self._afc_error(error), handle))
|
||||
return False
|
||||
return True
|
||||
|
||||
@ -1012,7 +1012,7 @@ class libiMobileDevice():
|
||||
byref(infolist)) & 0xFFFF
|
||||
file_stats = {}
|
||||
if error:
|
||||
self._log(" ERROR: %s" % self._afc_error(error))
|
||||
self._log_error(" ERROR: %s path:%s" % (self._afc_error(error), repr(path)))
|
||||
else:
|
||||
num_items = 0
|
||||
item_list = []
|
||||
@ -1049,7 +1049,7 @@ class libiMobileDevice():
|
||||
error = self.lib.afc_make_directory(byref(self.afc),
|
||||
str(path)) & 0xFFFF
|
||||
if error:
|
||||
self._log(" ERROR: %s" % self._afc_error(error))
|
||||
self._log_error(" ERROR: %s path:%s" % (self._afc_error(error), repr(path)))
|
||||
|
||||
return error
|
||||
|
||||
@ -1078,7 +1078,7 @@ class libiMobileDevice():
|
||||
str(directory),
|
||||
byref(dirs)) & 0xFFFF
|
||||
if error:
|
||||
self._log(" ERROR: %s" % self._afc_error(error))
|
||||
self._log_error(" ERROR: %s directory:%s" % (self._afc_error(error), repr(directory)))
|
||||
else:
|
||||
num_dirs = 0
|
||||
dir_list = []
|
||||
@ -1126,7 +1126,7 @@ class libiMobileDevice():
|
||||
error = self.lib.house_arrest_client_free(byref(self.house_arrest)) & 0xFFFF
|
||||
if error:
|
||||
error = error - 0x10000
|
||||
self._log(" ERROR: %s" % self._house_arrest_error(error))
|
||||
self._log_error(" ERROR: %s" % self._house_arrest_error(error))
|
||||
|
||||
def _house_arrest_client_new(self):
|
||||
'''
|
||||
@ -1302,7 +1302,7 @@ class libiMobileDevice():
|
||||
|
||||
if error:
|
||||
error = error - 0x10000
|
||||
self._log(" ERROR: %s" % self._idevice_error(error))
|
||||
self._log_error(" ERROR: %s" % self._idevice_error(error))
|
||||
|
||||
def _idevice_get_device_list(self):
|
||||
'''
|
||||
@ -1326,7 +1326,7 @@ class libiMobileDevice():
|
||||
self._log(" no connected devices")
|
||||
else:
|
||||
device_list = None
|
||||
self._log(" ERROR: %s" % self._idevice_error(error))
|
||||
self._log_error(" ERROR: %s" % self._idevice_error(error))
|
||||
else:
|
||||
index = 0
|
||||
while devices[index]:
|
||||
@ -1859,6 +1859,20 @@ class libiMobileDevice():
|
||||
else:
|
||||
debug_print()
|
||||
|
||||
def _log_error(self, *args):
|
||||
'''
|
||||
Print error message with location regardless of self.verbose
|
||||
'''
|
||||
arg1 = arg2 = ''
|
||||
|
||||
if len(args) > 0:
|
||||
arg1 = args[0]
|
||||
if len(args) > 1:
|
||||
arg2 = args[1]
|
||||
|
||||
debug_print(self.LOCATION_TEMPLATE.format(cls=self.__class__.__name__,
|
||||
func=sys._getframe(1).f_code.co_name, arg1=arg1, arg2=arg2))
|
||||
|
||||
def _log_location(self, *args):
|
||||
'''
|
||||
'''
|
||||
|
||||
@ -803,6 +803,20 @@ def load_builtin_fonts():
|
||||
if u'calibre Symbols' in fam:
|
||||
_rating_font = u'calibre Symbols'
|
||||
|
||||
def setup_gui_option_parser(parser):
|
||||
if islinux:
|
||||
parser.add_option('--detach', default=False, action='store_true',
|
||||
help='Detach from the controlling terminal, if any (linux only)')
|
||||
|
||||
def detach_gui():
|
||||
if islinux and not DEBUG and sys.stdout.isatty():
|
||||
# We are a GUI process running in a terminal so detach from the controlling terminal
|
||||
if os.fork() != 0:
|
||||
raise SystemExit(0)
|
||||
os.setsid()
|
||||
so, se = file(os.devnull, 'a+'), file(os.devnull, 'a+', 0)
|
||||
os.dup2(so.fileno(), sys.__stdout__.fileno())
|
||||
os.dup2(se.fileno(), sys.__stderr__.fileno())
|
||||
|
||||
class Application(QApplication):
|
||||
|
||||
@ -824,7 +838,6 @@ class Application(QApplication):
|
||||
self._file_open_paths = []
|
||||
self._file_open_lock = RLock()
|
||||
self.setup_styles(force_calibre_style)
|
||||
|
||||
if DEBUG:
|
||||
def notify(self, receiver, event):
|
||||
if self.redirect_notify:
|
||||
@ -862,27 +875,28 @@ class Application(QApplication):
|
||||
icon_map = {}
|
||||
pcache = {}
|
||||
for k, v in {
|
||||
'DialogYesButton': u'ok.png',
|
||||
'DialogNoButton': u'window-close.png',
|
||||
'DialogCloseButton': u'window-close.png',
|
||||
'DialogOkButton': u'ok.png',
|
||||
'DialogCancelButton': u'window-close.png',
|
||||
'DialogHelpButton': u'help.png',
|
||||
'DialogOpenButton': u'document_open.png',
|
||||
'DialogSaveButton': u'save.png',
|
||||
'DialogApplyButton': u'ok.png',
|
||||
'DialogDiscardButton': u'trash.png',
|
||||
'MessageBoxInformation': u'dialog_information.png',
|
||||
'MessageBoxWarning': u'dialog_warning.png',
|
||||
'MessageBoxCritical': u'dialog_error.png',
|
||||
'MessageBoxQuestion': u'dialog_question.png',
|
||||
'BrowserReload': u'view-refresh.png',
|
||||
# These two are used to calculate the sizes for the doc widget
|
||||
# title bar buttons, therefore, they have to exist. The actual
|
||||
# icon is not used.
|
||||
'TitleBarCloseButton': u'window-close.png',
|
||||
'TitleBarNormalButton': u'window-close.png',
|
||||
}.iteritems():
|
||||
'DialogYesButton': u'ok.png',
|
||||
'DialogNoButton': u'window-close.png',
|
||||
'DialogCloseButton': u'window-close.png',
|
||||
'DialogOkButton': u'ok.png',
|
||||
'DialogCancelButton': u'window-close.png',
|
||||
'DialogHelpButton': u'help.png',
|
||||
'DialogOpenButton': u'document_open.png',
|
||||
'DialogSaveButton': u'save.png',
|
||||
'DialogApplyButton': u'ok.png',
|
||||
'DialogDiscardButton': u'trash.png',
|
||||
'MessageBoxInformation': u'dialog_information.png',
|
||||
'MessageBoxWarning': u'dialog_warning.png',
|
||||
'MessageBoxCritical': u'dialog_error.png',
|
||||
'MessageBoxQuestion': u'dialog_question.png',
|
||||
'BrowserReload': u'view-refresh.png',
|
||||
# These two are used to calculate the sizes for the doc widget
|
||||
# title bar buttons, therefore, they have to exist. The actual
|
||||
# icon is not used.
|
||||
'TitleBarCloseButton': u'window-close.png',
|
||||
'TitleBarNormalButton': u'window-close.png',
|
||||
'DockWidgetCloseButton': u'window-close.png',
|
||||
}.iteritems():
|
||||
if v not in pcache:
|
||||
p = I(v)
|
||||
if isinstance(p, bytes):
|
||||
|
||||
@ -10,9 +10,9 @@ from functools import partial
|
||||
|
||||
from PyQt4.Qt import Qt, QAction, pyqtSignal
|
||||
|
||||
from calibre.constants import isosx
|
||||
from calibre.gui2 import error_dialog, Dispatcher, question_dialog, config, \
|
||||
open_local_file, info_dialog
|
||||
from calibre.constants import isosx, iswindows
|
||||
from calibre.gui2 import (
|
||||
error_dialog, Dispatcher, question_dialog, config, open_local_file, info_dialog)
|
||||
from calibre.gui2.dialogs.choose_format import ChooseFormatDialog
|
||||
from calibre.utils.config import prefs, tweaks
|
||||
from calibre.ptempfile import PersistentTemporaryFile
|
||||
@ -119,8 +119,26 @@ class ViewAction(InterfaceAction):
|
||||
self.gui.job_manager.launch_gui_app(viewer,
|
||||
kwargs=dict(args=args))
|
||||
else:
|
||||
if iswindows:
|
||||
from calibre.utils.file_associations import file_assoc_windows
|
||||
ext = name.rpartition('.')[-1]
|
||||
if ext:
|
||||
try:
|
||||
prog = file_assoc_windows(ext)
|
||||
except Exception:
|
||||
prog = None
|
||||
if prog and prog.lower().endswith('calibre.exe'):
|
||||
name = os.path.basename(name)
|
||||
return error_dialog(
|
||||
self.gui, _('No associated program'), _(
|
||||
'Windows will try to open %s with calibre itself'
|
||||
' resulting in a duplicate in your calibre library. You'
|
||||
' should install some program capable of viewing this'
|
||||
' file format and tell windows to use that program to open'
|
||||
' files of this type.') % name, show=True)
|
||||
|
||||
open_local_file(name)
|
||||
time.sleep(2) # User feedback
|
||||
time.sleep(2) # User feedback
|
||||
finally:
|
||||
self.gui.unsetCursor()
|
||||
|
||||
@ -145,7 +163,8 @@ class ViewAction(InterfaceAction):
|
||||
all_fmts = set([])
|
||||
for x in formats:
|
||||
if x:
|
||||
for f in x: all_fmts.add(f)
|
||||
for f in x:
|
||||
all_fmts.add(f)
|
||||
if not all_fmts:
|
||||
error_dialog(self.gui, _('Format unavailable'),
|
||||
_('Selected books have no formats'), show=True)
|
||||
@ -257,7 +276,7 @@ class ViewAction(InterfaceAction):
|
||||
self.build_menus(db)
|
||||
|
||||
def view_device_book(self, path):
|
||||
pt = PersistentTemporaryFile('_view_device_book'+\
|
||||
pt = PersistentTemporaryFile('_view_device_book'+
|
||||
os.path.splitext(path)[1])
|
||||
self.persistent_files.append(pt)
|
||||
pt.close()
|
||||
|
||||
@ -12,8 +12,9 @@ from calibre import prints, plugins, force_unicode
|
||||
from calibre.constants import (iswindows, __appname__, isosx, DEBUG, islinux,
|
||||
filesystem_encoding, get_portable_base)
|
||||
from calibre.utils.ipc import gui_socket_address, RC
|
||||
from calibre.gui2 import (ORG_NAME, APP_UID, initialize_file_icon_provider,
|
||||
Application, choose_dir, error_dialog, question_dialog, gprefs)
|
||||
from calibre.gui2 import (
|
||||
ORG_NAME, APP_UID, initialize_file_icon_provider, Application, choose_dir,
|
||||
error_dialog, question_dialog, gprefs, detach_gui, setup_gui_option_parser)
|
||||
from calibre.gui2.main_window import option_parser as _option_parser
|
||||
from calibre.utils.config import prefs, dynamic
|
||||
|
||||
@ -46,6 +47,7 @@ path_to_ebook to the database.
|
||||
help=_('Cause a running calibre instance, if any, to be'
|
||||
' shutdown. Note that if there are running jobs, they '
|
||||
'will be silently aborted, so use with care.'))
|
||||
setup_gui_option_parser(parser)
|
||||
return parser
|
||||
|
||||
def find_portable_library():
|
||||
@ -84,6 +86,8 @@ def find_portable_library():
|
||||
def init_qt(args):
|
||||
parser = option_parser()
|
||||
opts, args = parser.parse_args(args)
|
||||
if getattr(opts, 'detach', False):
|
||||
detach_gui()
|
||||
find_portable_library()
|
||||
if opts.with_library is not None:
|
||||
libpath = os.path.expanduser(opts.with_library)
|
||||
|
||||
@ -52,6 +52,7 @@ class Boss(QObject):
|
||||
fl.edit_file.connect(self.edit_file_requested)
|
||||
self.gui.central.current_editor_changed.connect(self.apply_current_editor_state)
|
||||
self.gui.central.close_requested.connect(self.editor_close_requested)
|
||||
self.gui.central.search_panel.search_triggered.connect(self.search)
|
||||
|
||||
def mkdtemp(self, prefix=''):
|
||||
self.container_count += 1
|
||||
@ -258,6 +259,84 @@ class Boss(QObject):
|
||||
self.update_global_history_actions()
|
||||
# }}}
|
||||
|
||||
def mark_selected_text(self):
|
||||
ed = self.gui.central.current_editor
|
||||
if ed is not None:
|
||||
ed.mark_selected_text()
|
||||
if ed.has_marked_text:
|
||||
self.gui.central.search_panel.set_where('selected-text')
|
||||
|
||||
def search(self, action, overrides=None):
|
||||
' Run a search/replace '
|
||||
sp = self.gui.central.search_panel
|
||||
# Ensure the search panel is visible
|
||||
sp.setVisible(True)
|
||||
ed = self.gui.central.current_editor
|
||||
name = None
|
||||
for n, x in editors.iteritems():
|
||||
if x is ed:
|
||||
name = n
|
||||
break
|
||||
state = sp.state
|
||||
if overrides:
|
||||
state.update(overrides)
|
||||
searchable_names = self.gui.file_list.searchable_names
|
||||
where = state['where']
|
||||
err = None
|
||||
if name is None and where in {'current', 'selected-text'}:
|
||||
err = _('No file is being edited.')
|
||||
elif where == 'selected' and not searchable_names['selected']:
|
||||
err = _('No files are selected in the Files Browser')
|
||||
elif where == 'selected-text' and not ed.has_marked_text:
|
||||
err = _('No text is marked. First select some text, and then use'
|
||||
' The "Mark selected text" action in the Search menu to mark it.')
|
||||
if not err and not state['find']:
|
||||
err = _('No search query specified')
|
||||
if err:
|
||||
return error_dialog(self.gui, _('Cannot search'), err, show=True)
|
||||
del err
|
||||
if where == 'current':
|
||||
files = [name]
|
||||
editor = ed
|
||||
elif where in {'styles', 'text', 'selected'}:
|
||||
files = searchable_names[where]
|
||||
if name in files:
|
||||
editor = ed
|
||||
else:
|
||||
common = set(editors).intersection(set(files))
|
||||
if common:
|
||||
name = next(x for x in files if x in common)
|
||||
editor = editors[name]
|
||||
self.gui.central.show_editor(editor)
|
||||
else:
|
||||
pass # TODO: Find the first name with a match and open its editor
|
||||
else:
|
||||
files = [name]
|
||||
pass # marked text TODO: Implement this
|
||||
|
||||
def no_match():
|
||||
return error_dialog(
|
||||
self.gui, _('Not found'), _(
|
||||
'No matches were found for %s') % state['find'], show=True)
|
||||
|
||||
pat = sp.get_regex(state)
|
||||
|
||||
def do_find():
|
||||
found = editor.find(pat)
|
||||
if found:
|
||||
return
|
||||
if len(files) == 1:
|
||||
if not state['wrap']:
|
||||
return no_match()
|
||||
found = editor.find(pat, wrap=True)
|
||||
if not found:
|
||||
return no_match()
|
||||
else:
|
||||
pass # TODO: handle multiple file search
|
||||
|
||||
if action == 'find':
|
||||
return do_find()
|
||||
|
||||
def save_book(self):
|
||||
c = current_container()
|
||||
for name, ed in editors.iteritems():
|
||||
@ -278,19 +357,26 @@ class Boss(QObject):
|
||||
_('Saving of the book failed. Click "Show Details"'
|
||||
' for more information.'), det_msg=tb, show=True)
|
||||
|
||||
def init_editor(self, name, editor, data=None):
|
||||
editor.undo_redo_state_changed.connect(self.editor_undo_redo_state_changed)
|
||||
editor.data_changed.connect(self.editor_data_changed)
|
||||
editor.copy_available_state_changed.connect(self.editor_copy_available_state_changed)
|
||||
if data is not None:
|
||||
editor.data = data
|
||||
editor.modification_state_changed.connect(self.editor_modification_state_changed)
|
||||
self.gui.central.add_editor(name, editor)
|
||||
|
||||
def edit_file(self, name, syntax):
|
||||
editor = editors.get(name, None)
|
||||
if editor is None:
|
||||
editor = editors[name] = editor_from_syntax(syntax, self.gui.editor_tabs)
|
||||
editor.undo_redo_state_changed.connect(self.editor_undo_redo_state_changed)
|
||||
editor.data_changed.connect(self.editor_data_changed)
|
||||
editor.copy_available_state_changed.connect(self.editor_copy_available_state_changed)
|
||||
c = current_container()
|
||||
with c.open(name) as f:
|
||||
editor.data = c.decode(f.read())
|
||||
editor.modification_state_changed.connect(self.editor_modification_state_changed)
|
||||
self.gui.central.add_editor(name, editor)
|
||||
self.gui.central.show_editor(editor)
|
||||
data = current_container().raw_data(name)
|
||||
self.init_editor(name, editor, data)
|
||||
self.show_editor(name)
|
||||
|
||||
def show_editor(self, name):
|
||||
self.gui.central.show_editor(editors[name])
|
||||
editors[name].set_focus()
|
||||
|
||||
def edit_file_requested(self, name, syntax, mime):
|
||||
if name in editors:
|
||||
|
||||
@ -6,6 +6,8 @@ from __future__ import (unicode_literals, division, absolute_import,
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
|
||||
from PyQt4.Qt import QTextCharFormat
|
||||
|
||||
from calibre.ebooks.oeb.base import OEB_DOCS, OEB_STYLES
|
||||
from calibre.ebooks.oeb.polish.container import guess_type
|
||||
|
||||
@ -25,3 +27,11 @@ def editor_from_syntax(syntax, parent=None):
|
||||
from calibre.gui2.tweak_book.editor.widget import Editor
|
||||
return Editor(syntax, parent=parent)
|
||||
|
||||
SYNTAX_PROPERTY = QTextCharFormat.UserProperty
|
||||
|
||||
class SyntaxTextCharFormat(QTextCharFormat):
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
QTextCharFormat.__init__(self, *args, **kwargs)
|
||||
self.setProperty(SYNTAX_PROPERTY, True)
|
||||
|
||||
|
||||
@ -8,10 +8,9 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
|
||||
import re
|
||||
|
||||
from calibre.gui2.tweak_book.editor import SyntaxTextCharFormat
|
||||
from calibre.gui2.tweak_book.editor.syntax.base import SyntaxHighlighter
|
||||
|
||||
from PyQt4.Qt import QTextCharFormat
|
||||
|
||||
space_pat = re.compile(r'[ \n\t\r\f]+')
|
||||
cdo_pat = re.compile(r'/\*')
|
||||
sheet_tokens = [(re.compile(k), v, n) for k, v, n in [
|
||||
@ -242,7 +241,7 @@ def create_formats(highlighter):
|
||||
'unknown-normal': _('Invalid text'),
|
||||
'unterminated-string': _('Unterminated string'),
|
||||
}.iteritems():
|
||||
f = formats[name] = QTextCharFormat(formats['error'])
|
||||
f = formats[name] = SyntaxTextCharFormat(formats['error'])
|
||||
f.setToolTip(msg)
|
||||
return formats
|
||||
|
||||
|
||||
@ -9,8 +9,9 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
import re
|
||||
from functools import partial
|
||||
|
||||
from PyQt4.Qt import (QTextCharFormat, QFont)
|
||||
from PyQt4.Qt import QFont
|
||||
|
||||
from calibre.gui2.tweak_book.editor import SyntaxTextCharFormat
|
||||
from calibre.gui2.tweak_book.editor.syntax.base import SyntaxHighlighter, run_loop
|
||||
from calibre.gui2.tweak_book.editor.syntax.css import create_formats as create_css_formats, state_map as css_state_map, State as CSSState
|
||||
|
||||
@ -109,7 +110,7 @@ def mark_nbsp(state, text, nbsp_format):
|
||||
ans = []
|
||||
fmt = None
|
||||
if state.bold or state.italic:
|
||||
fmt = QTextCharFormat()
|
||||
fmt = SyntaxTextCharFormat()
|
||||
if state.bold:
|
||||
fmt.setFontWeight(QFont.Bold)
|
||||
if state.italic:
|
||||
@ -313,9 +314,9 @@ def create_formats(highlighter):
|
||||
'bad-closing': _('A closing tag must contain only the tag name and nothing else'),
|
||||
'no-attr-value': _('Expecting an attribute value'),
|
||||
}.iteritems():
|
||||
f = formats[name] = QTextCharFormat(formats['error'])
|
||||
f = formats[name] = SyntaxTextCharFormat(formats['error'])
|
||||
f.setToolTip(msg)
|
||||
f = formats['title'] = QTextCharFormat()
|
||||
f = formats['title'] = SyntaxTextCharFormat()
|
||||
f.setFontWeight(QFont.Bold)
|
||||
return formats
|
||||
|
||||
|
||||
@ -9,16 +9,20 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
import textwrap
|
||||
from future_builtins import map
|
||||
|
||||
import regex
|
||||
from PyQt4.Qt import (
|
||||
QPlainTextEdit, QFontDatabase, QToolTip, QPalette, QFont,
|
||||
QTextEdit, QTextFormat, QWidget, QSize, QPainter, Qt, QRect)
|
||||
|
||||
from calibre.gui2.tweak_book import tprefs
|
||||
from calibre.gui2.tweak_book.editor import SYNTAX_PROPERTY
|
||||
from calibre.gui2.tweak_book.editor.themes import THEMES, default_theme, theme_color
|
||||
from calibre.gui2.tweak_book.editor.syntax.base import SyntaxHighlighter
|
||||
from calibre.gui2.tweak_book.editor.syntax.html import HTMLHighlighter, XMLHighlighter
|
||||
from calibre.gui2.tweak_book.editor.syntax.css import CSSHighlighter
|
||||
|
||||
PARAGRAPH_SEPARATOR = '\u2029'
|
||||
|
||||
_dff = None
|
||||
def default_font_family():
|
||||
global _dff
|
||||
@ -48,6 +52,8 @@ class TextEdit(QPlainTextEdit):
|
||||
|
||||
def __init__(self, parent=None):
|
||||
QPlainTextEdit.__init__(self, parent)
|
||||
self.current_cursor_line = None
|
||||
self.current_search_mark = None
|
||||
self.highlighter = SyntaxHighlighter(self)
|
||||
self.apply_settings()
|
||||
self.setMouseTracking(True)
|
||||
@ -106,6 +112,7 @@ class TextEdit(QPlainTextEdit):
|
||||
w = self.fontMetrics()
|
||||
self.number_width = max(map(lambda x:w.width(str(x)), xrange(10)))
|
||||
self.size_hint = QSize(100 * w.averageCharWidth(), 50 * w.height())
|
||||
self.highlight_color = theme_color(theme, 'HighlightRegion', 'bg')
|
||||
# }}}
|
||||
|
||||
def load_text(self, text, syntax='html'):
|
||||
@ -126,6 +133,69 @@ class TextEdit(QPlainTextEdit):
|
||||
self.setTextCursor(c)
|
||||
self.ensureCursorVisible()
|
||||
|
||||
def update_extra_selections(self):
|
||||
sel = []
|
||||
if self.current_cursor_line is not None:
|
||||
sel.append(self.current_cursor_line)
|
||||
if self.current_search_mark is not None:
|
||||
sel.append(self.current_search_mark)
|
||||
self.setExtraSelections(sel)
|
||||
|
||||
def mark_selected_text(self):
|
||||
sel = QTextEdit.ExtraSelection()
|
||||
sel.format.setBackground(self.highlight_color)
|
||||
sel.cursor = self.textCursor()
|
||||
if sel.cursor.hasSelection():
|
||||
self.current_search_mark = sel
|
||||
c = self.textCursor()
|
||||
c.clearSelection()
|
||||
self.setTextCursor(c)
|
||||
else:
|
||||
self.current_search_mark = None
|
||||
self.update_extra_selections()
|
||||
|
||||
def find(self, pat, wrap=False):
|
||||
reverse = pat.flags & regex.REVERSE
|
||||
c = self.textCursor()
|
||||
c.clearSelection()
|
||||
pos = c.Start if reverse else c.End
|
||||
if wrap:
|
||||
pos = c.End if reverse else c.Start
|
||||
c.movePosition(pos, c.KeepAnchor)
|
||||
raw = unicode(c.selectedText()).replace(PARAGRAPH_SEPARATOR, '\n')
|
||||
m = pat.search(raw)
|
||||
if m is None:
|
||||
return False
|
||||
start, end = m.span()
|
||||
if start == end:
|
||||
return False
|
||||
if wrap:
|
||||
if reverse:
|
||||
textpos = c.anchor()
|
||||
start, end = textpos + end, textpos + start
|
||||
else:
|
||||
if reverse:
|
||||
# Put the cursor at the start of the match
|
||||
start, end = end, start
|
||||
else:
|
||||
textpos = c.anchor()
|
||||
start, end = textpos + start, textpos + end
|
||||
c.clearSelection()
|
||||
c.setPosition(start)
|
||||
c.setPosition(end, c.KeepAnchor)
|
||||
self.setTextCursor(c)
|
||||
return True
|
||||
|
||||
def replace(self, pat, template):
|
||||
c = self.textCursor()
|
||||
raw = unicode(c.selectedText()).replace(PARAGRAPH_SEPARATOR, '\n')
|
||||
m = pat.fullmatch(raw)
|
||||
if m is None:
|
||||
return False
|
||||
text = m.expand(template)
|
||||
c.insertText(text)
|
||||
return True
|
||||
|
||||
# Line numbers and cursor line {{{
|
||||
def highlight_cursor_line(self):
|
||||
sel = QTextEdit.ExtraSelection()
|
||||
@ -133,7 +203,8 @@ class TextEdit(QPlainTextEdit):
|
||||
sel.format.setProperty(QTextFormat.FullWidthSelection, True)
|
||||
sel.cursor = self.textCursor()
|
||||
sel.cursor.clearSelection()
|
||||
self.setExtraSelections([sel])
|
||||
self.current_cursor_line = sel
|
||||
self.update_extra_selections()
|
||||
# Update the cursor line's line number in the line number area
|
||||
try:
|
||||
self.line_number_area.update(0, self.last_current_lnum[0], self.line_number_area.width(), self.last_current_lnum[1])
|
||||
@ -211,7 +282,7 @@ class TextEdit(QPlainTextEdit):
|
||||
return
|
||||
pos = cursor.positionInBlock()
|
||||
for r in cursor.block().layout().additionalFormats():
|
||||
if r.start <= pos < r.start + r.length:
|
||||
if r.start <= pos < r.start + r.length and r.format.property(SYNTAX_PROPERTY).toBool():
|
||||
return r.format
|
||||
|
||||
def show_tooltip(self, ev):
|
||||
|
||||
@ -8,7 +8,9 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
|
||||
from collections import namedtuple
|
||||
|
||||
from PyQt4.Qt import (QColor, QTextCharFormat, QBrush, QFont, QApplication, QPalette)
|
||||
from PyQt4.Qt import (QColor, QBrush, QFont, QApplication, QPalette)
|
||||
|
||||
from calibre.gui2.tweak_book.editor import SyntaxTextCharFormat
|
||||
|
||||
underline_styles = {'single', 'dash', 'dot', 'dash_dot', 'dash_dot_dot', 'wave', 'spell'}
|
||||
|
||||
@ -32,6 +34,7 @@ SOLARIZED = \
|
||||
CursorLine bg={base02}
|
||||
CursorColumn bg={base02}
|
||||
ColorColumn bg={base02}
|
||||
HighlightRegion bg={base00}
|
||||
MatchParen fg={red} bg={base01} bold
|
||||
Pmenu fg={base0} bg={base02}
|
||||
PmenuSel fg={base01} bg={base2}
|
||||
@ -66,6 +69,7 @@ THEMES = {
|
||||
CursorLine bg={cursor_loc}
|
||||
CursorColumn bg={cursor_loc}
|
||||
ColorColumn bg={cursor_loc}
|
||||
HighlightRegion bg=323232
|
||||
MatchParen fg=f6f3e8 bg=857b6f bold
|
||||
Pmenu fg=f6f3e8 bg=444444
|
||||
PmenuSel fg=yellow bg={identifier}
|
||||
@ -104,6 +108,7 @@ THEMES = {
|
||||
CursorLine bg={cursor_loc}
|
||||
CursorColumn bg={cursor_loc}
|
||||
ColorColumn bg={cursor_loc}
|
||||
HighlightRegion bg=E3F988
|
||||
MatchParen fg=white bg=80a090 bold
|
||||
Pmenu fg=white bg=808080
|
||||
PmenuSel fg=white bg=808080
|
||||
@ -130,7 +135,7 @@ THEMES = {
|
||||
Error us=wave uc=red
|
||||
|
||||
'''.format(
|
||||
cursor_loc='white',
|
||||
cursor_loc='F8DE7E',
|
||||
identifier='7b5694',
|
||||
comment='a0b0c0',
|
||||
string='4070a0',
|
||||
@ -198,10 +203,10 @@ def u(x):
|
||||
if 'Dot' in x:
|
||||
return x + 'Line'
|
||||
return x + 'Underline'
|
||||
underline_styles = {x:getattr(QTextCharFormat, u(x)) for x in underline_styles}
|
||||
underline_styles = {x:getattr(SyntaxTextCharFormat, u(x)) for x in underline_styles}
|
||||
|
||||
def highlight_to_char_format(h):
|
||||
ans = QTextCharFormat()
|
||||
ans = SyntaxTextCharFormat()
|
||||
if h.bold:
|
||||
ans.setFontWeight(QFont.Bold)
|
||||
if h.italic:
|
||||
|
||||
@ -58,12 +58,28 @@ class Editor(QMainWindow):
|
||||
if current != raw:
|
||||
self.editor.replace_text(raw)
|
||||
|
||||
def set_focus(self):
|
||||
self.editor.setFocus(Qt.OtherFocusReason)
|
||||
|
||||
def undo(self):
|
||||
self.editor.undo()
|
||||
|
||||
def redo(self):
|
||||
self.editor.redo()
|
||||
|
||||
def mark_selected_text(self):
|
||||
self.editor.mark_selected_text()
|
||||
|
||||
def find(self, *args, **kwargs):
|
||||
return self.editor.find(*args, **kwargs)
|
||||
|
||||
def replace(self, *args, **kwargs):
|
||||
return self.editor.replace(*args, **kwargs)
|
||||
|
||||
@property
|
||||
def has_marked_text(self):
|
||||
return self.editor.current_search_mark is not None
|
||||
|
||||
@dynamic_property
|
||||
def is_modified(self):
|
||||
def fget(self):
|
||||
|
||||
@ -338,6 +338,26 @@ class FileList(QTreeWidget):
|
||||
syntax = {'text':'html', 'styles':'css'}.get(category, None)
|
||||
self.edit_file.emit(name, syntax, mime)
|
||||
|
||||
@property
|
||||
def all_files(self):
|
||||
return (category.child(i) for category in self.categories.itervalues() for i in xrange(category.childCount()))
|
||||
|
||||
@property
|
||||
def searchable_names(self):
|
||||
ans = {'text':[], 'styles':[], 'selected':[]}
|
||||
for item in self.all_files:
|
||||
category = unicode(item.data(0, CATEGORY_ROLE).toString())
|
||||
mime = unicode(item.data(0, MIME_ROLE).toString())
|
||||
name = unicode(item.data(0, NAME_ROLE).toString())
|
||||
ok = category in {'text', 'styles'}
|
||||
if ok:
|
||||
ans[category].append(name)
|
||||
if not ok and category == 'misc':
|
||||
ok = mime in {guess_type('a.'+x) for x in ('opf', 'ncx', 'txt', 'xml')}
|
||||
if ok and item.isSelected():
|
||||
ans['selected'].append(name)
|
||||
return ans
|
||||
|
||||
class FileListWidget(QWidget):
|
||||
|
||||
delete_requested = pyqtSignal(object, object)
|
||||
@ -359,4 +379,7 @@ class FileListWidget(QWidget):
|
||||
def build(self, container, preserve_state=True):
|
||||
self.file_list.build(container, preserve_state=preserve_state)
|
||||
|
||||
@property
|
||||
def searchable_names(self):
|
||||
return self.file_list.searchable_names
|
||||
|
||||
|
||||
@ -11,17 +11,20 @@ import sys, os
|
||||
from PyQt4.Qt import QIcon
|
||||
|
||||
from calibre.constants import islinux
|
||||
from calibre.gui2 import Application, ORG_NAME, APP_UID
|
||||
from calibre.gui2 import Application, ORG_NAME, APP_UID, setup_gui_option_parser, detach_gui
|
||||
from calibre.ptempfile import reset_base_dir
|
||||
from calibre.utils.config import OptionParser
|
||||
from calibre.gui2.tweak_book.ui import Main
|
||||
|
||||
def option_parser():
|
||||
return OptionParser('''\
|
||||
parser = OptionParser('''\
|
||||
%prog [opts] [path_to_ebook]
|
||||
|
||||
Launch the calibre tweak book tool.
|
||||
''')
|
||||
setup_gui_option_parser(parser)
|
||||
return parser
|
||||
|
||||
|
||||
def main(args=sys.argv):
|
||||
# Ensure we can continue to function if GUI is closed
|
||||
@ -30,6 +33,8 @@ def main(args=sys.argv):
|
||||
|
||||
parser = option_parser()
|
||||
opts, args = parser.parse_args(args)
|
||||
if getattr(opts, 'detach', False):
|
||||
detach_gui()
|
||||
override = 'calibre-tweak-book' if islinux else None
|
||||
app = Application(args, override_program_name=override)
|
||||
app.load_builtin_fonts()
|
||||
|
||||
287
src/calibre/gui2/tweak_book/search.py
Normal file
287
src/calibre/gui2/tweak_book/search.py
Normal file
@ -0,0 +1,287 @@
|
||||
#!/usr/bin/env python
|
||||
# vim:fileencoding=utf-8
|
||||
from __future__ import (unicode_literals, division, absolute_import,
|
||||
print_function)
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
|
||||
from PyQt4.Qt import (
|
||||
QWidget, QToolBar, Qt, QHBoxLayout, QSize, QIcon, QGridLayout, QLabel,
|
||||
QPushButton, pyqtSignal, QComboBox, QCheckBox, QSizePolicy)
|
||||
|
||||
import regex
|
||||
|
||||
from calibre.gui2.widgets2 import HistoryLineEdit2
|
||||
from calibre.gui2.tweak_book import tprefs
|
||||
|
||||
REGEX_FLAGS = regex.VERSION1 | regex.WORD | regex.FULLCASE | regex.MULTILINE | regex.UNICODE
|
||||
|
||||
# The search panel {{{
|
||||
|
||||
class PushButton(QPushButton):
|
||||
|
||||
def __init__(self, text, action, parent):
|
||||
QPushButton.__init__(self, text, parent)
|
||||
self.clicked.connect(lambda : parent.search_triggered.emit(action))
|
||||
|
||||
class SearchWidget(QWidget):
|
||||
|
||||
DEFAULT_STATE = {
|
||||
'mode': 'normal',
|
||||
'where': 'current',
|
||||
'case_sensitive': False,
|
||||
'direction': 'down',
|
||||
'wrap': True,
|
||||
'dot_all': False,
|
||||
}
|
||||
|
||||
search_triggered = pyqtSignal(object)
|
||||
|
||||
def __init__(self, parent=None):
|
||||
QWidget.__init__(self, parent)
|
||||
self.l = l = QGridLayout(self)
|
||||
l.setContentsMargins(0, 0, 0, 0)
|
||||
self.setLayout(l)
|
||||
|
||||
self.fl = fl = QLabel(_('&Find:'))
|
||||
fl.setAlignment(Qt.AlignRight | Qt.AlignCenter)
|
||||
self.find_text = ft = HistoryLineEdit2(self)
|
||||
ft.initialize('tweak_book_find_edit')
|
||||
ft.returnPressed.connect(lambda : self.search_triggered.emit('find'))
|
||||
fl.setBuddy(ft)
|
||||
l.addWidget(fl, 0, 0)
|
||||
l.addWidget(ft, 0, 1)
|
||||
|
||||
self.rl = rl = QLabel(_('&Replace:'))
|
||||
rl.setAlignment(Qt.AlignRight | Qt.AlignCenter)
|
||||
self.replace_text = rt = HistoryLineEdit2(self)
|
||||
rt.initialize('tweak_book_replace_edit')
|
||||
rl.setBuddy(rt)
|
||||
l.addWidget(rl, 1, 0)
|
||||
l.addWidget(rt, 1, 1)
|
||||
l.setColumnStretch(1, 10)
|
||||
|
||||
self.fb = fb = PushButton(_('&Find'), 'find', self)
|
||||
self.rfb = rfb = PushButton(_('Replace a&nd Find'), 'replace-find', self)
|
||||
self.rb = rb = PushButton(_('&Replace'), 'replace', self)
|
||||
self.rab = rab = PushButton(_('Replace &all'), 'replace-all', self)
|
||||
l.addWidget(fb, 0, 2)
|
||||
l.addWidget(rfb, 0, 3)
|
||||
l.addWidget(rb, 1, 2)
|
||||
l.addWidget(rab, 1, 3)
|
||||
|
||||
self.ml = ml = QLabel(_('&Mode:'))
|
||||
self.ol = ol = QHBoxLayout()
|
||||
ml.setAlignment(Qt.AlignRight | Qt.AlignCenter)
|
||||
l.addWidget(ml, 2, 0)
|
||||
l.addLayout(ol, 2, 1, 1, 3)
|
||||
self.mode_box = mb = QComboBox(self)
|
||||
mb.setSizePolicy(QSizePolicy.Maximum, QSizePolicy.Maximum)
|
||||
mb.addItems([_('Normal'), _('Regex')])
|
||||
mb.setToolTip('<style>dd {margin-bottom: 1.5ex}</style>' + _(
|
||||
'''Select how the search expression is interpreted
|
||||
<dl>
|
||||
<dt><b>Normal</b></dt>
|
||||
<dd>The search expression is treated as normal text, calibre will look for the exact text.</dd>
|
||||
<dt><b>Regex</b></dt>
|
||||
<dd>The search expression is interpreted as a regular expression. See the User Manual for more help on using regular expressions.</dd>
|
||||
</dl>'''))
|
||||
ml.setBuddy(mb)
|
||||
ol.addWidget(mb)
|
||||
|
||||
self.where_box = wb = QComboBox(self)
|
||||
wb.setSizePolicy(QSizePolicy.Maximum, QSizePolicy.Maximum)
|
||||
wb.addItems([_('Current file'), _('All text files'), _('All style files'), _('Selected files'), _('Selected text')])
|
||||
wb.setToolTip('<style>dd {margin-bottom: 1.5ex}</style>' + _(
|
||||
'''
|
||||
Where to search/replace:
|
||||
<dl>
|
||||
<dt><b>Current file</b></dt>
|
||||
<dd>Search only inside the currently opened file</dd>
|
||||
<dt><b>All text files</b></dt>
|
||||
<dd>Search in all text (HTML) files</dd>
|
||||
<dt><b>All style files</b></dt>
|
||||
<dd>Search in all style (CSS) files</dd>
|
||||
<dt><b>Selected files</b></dt>
|
||||
<dd>Search in the files currently selected in the Files Browser</dd>
|
||||
<dt><b>Selected text</b></dt>
|
||||
<dd>Search only within the selected text in the currently opened file</dd>
|
||||
</dl>'''))
|
||||
ol.addWidget(wb)
|
||||
|
||||
self.direction_box = db = QComboBox(self)
|
||||
db.setSizePolicy(QSizePolicy.Maximum, QSizePolicy.Maximum)
|
||||
db.addItems([_('Down'), _('Up')])
|
||||
db.setToolTip('<style>dd {margin-bottom: 1.5ex}</style>' + _(
|
||||
'''
|
||||
Direction to search:
|
||||
<dl>
|
||||
<dt><b>Down</b></dt>
|
||||
<dd>Search for the next match from your current position</dd>
|
||||
<dt><b>Up</b></dt>
|
||||
<dd>Search for the previous match from your current position</dd>
|
||||
</dl>'''))
|
||||
ol.addWidget(db)
|
||||
|
||||
self.cs = cs = QCheckBox(_('&Case sensitive'))
|
||||
cs.setSizePolicy(QSizePolicy.Maximum, QSizePolicy.Maximum)
|
||||
ol.addWidget(cs)
|
||||
|
||||
self.wr = wr = QCheckBox(_('&Wrap'))
|
||||
wr.setToolTip('<p>'+_('When searching reaches the end, wrap around to the beginning and continue the search'))
|
||||
wr.setSizePolicy(QSizePolicy.Maximum, QSizePolicy.Maximum)
|
||||
ol.addWidget(wr)
|
||||
|
||||
self.da = da = QCheckBox(_('&Dot all'))
|
||||
da.setToolTip('<p>'+_("Make the '.' special character match any character at all, including a newline"))
|
||||
da.setSizePolicy(QSizePolicy.Maximum, QSizePolicy.Maximum)
|
||||
ol.addWidget(da)
|
||||
|
||||
self.mode_box.currentIndexChanged[int].connect(self.da.setVisible)
|
||||
|
||||
ol.addStretch(10)
|
||||
|
||||
@dynamic_property
|
||||
def mode(self):
|
||||
def fget(self):
|
||||
return 'normal' if self.mode_box.currentIndex() == 0 else 'regex'
|
||||
def fset(self, val):
|
||||
self.mode_box.setCurrentIndex({'regex':1}.get(val, 0))
|
||||
self.da.setVisible(self.mode == 'regex')
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
@dynamic_property
|
||||
def find(self):
|
||||
def fget(self):
|
||||
return unicode(self.find_text.text())
|
||||
def fset(self, val):
|
||||
self.find_text.setText(val)
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
@dynamic_property
|
||||
def replace(self):
|
||||
def fget(self):
|
||||
return unicode(self.replace_text.text())
|
||||
def fset(self, val):
|
||||
self.replace_text.setText(val)
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
@dynamic_property
|
||||
def where(self):
|
||||
wm = {0:'current', 1:'text', 2:'styles', 3:'selected', 4:'selected-text'}
|
||||
def fget(self):
|
||||
return wm[self.where_box.currentIndex()]
|
||||
def fset(self, val):
|
||||
self.where_box.setCurrentIndex({v:k for k, v in wm.iteritems()}[val])
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
@dynamic_property
|
||||
def case_sensitive(self):
|
||||
def fget(self):
|
||||
return self.cs.isChecked()
|
||||
def fset(self, val):
|
||||
self.cs.setChecked(bool(val))
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
@dynamic_property
|
||||
def direction(self):
|
||||
def fget(self):
|
||||
return 'down' if self.direction_box.currentIndex() == 0 else 'up'
|
||||
def fset(self, val):
|
||||
self.direction_box.setCurrentIndex(1 if val == 'up' else 0)
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
@dynamic_property
|
||||
def wrap(self):
|
||||
def fget(self):
|
||||
return self.wr.isChecked()
|
||||
def fset(self, val):
|
||||
self.wr.setChecked(bool(val))
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
@dynamic_property
|
||||
def dot_all(self):
|
||||
def fget(self):
|
||||
return self.da.isChecked()
|
||||
def fset(self, val):
|
||||
self.da.setChecked(bool(val))
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
@dynamic_property
|
||||
def state(self):
|
||||
def fget(self):
|
||||
return {x:getattr(self, x) for x in self.DEFAULT_STATE}
|
||||
def fset(self, val):
|
||||
for x in self.DEFAULT_STATE:
|
||||
if x in val:
|
||||
setattr(self, x, val[x])
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
def restore_state(self):
|
||||
self.state = tprefs.get('find-widget-state', self.DEFAULT_STATE)
|
||||
if self.where == 'selected-text':
|
||||
self.where = self.DEFAULT_STATE['where']
|
||||
|
||||
def save_state(self):
|
||||
tprefs.set('find-widget-state', self.state)
|
||||
|
||||
# }}}
|
||||
|
||||
regex_cache = {}
|
||||
|
||||
class SearchPanel(QWidget):
|
||||
|
||||
search_triggered = pyqtSignal(object)
|
||||
|
||||
def __init__(self, parent=None):
|
||||
QWidget.__init__(self, parent)
|
||||
self.l = l = QHBoxLayout()
|
||||
self.setLayout(l)
|
||||
l.setContentsMargins(0, 0, 0, 0)
|
||||
self.t = t = QToolBar(self)
|
||||
l.addWidget(t)
|
||||
t.setOrientation(Qt.Vertical)
|
||||
t.setIconSize(QSize(12, 12))
|
||||
t.setMovable(False)
|
||||
t.setFloatable(False)
|
||||
t.cl = ac = t.addAction(QIcon(I('window-close.png')), _('Close search panel'))
|
||||
ac.triggered.connect(self.hide_panel)
|
||||
self.widget = SearchWidget(self)
|
||||
l.addWidget(self.widget)
|
||||
self.restore_state, self.save_state = self.widget.restore_state, self.widget.save_state
|
||||
self.widget.search_triggered.connect(self.search_triggered)
|
||||
|
||||
def hide_panel(self):
|
||||
self.setVisible(False)
|
||||
|
||||
def show_panel(self):
|
||||
self.setVisible(True)
|
||||
self.widget.find_text.setFocus(Qt.OtherFocusReason)
|
||||
|
||||
@property
|
||||
def state(self):
|
||||
ans = self.widget.state
|
||||
ans['find'] = self.widget.find
|
||||
ans['replace'] = self.widget.replace
|
||||
return ans
|
||||
|
||||
def set_where(self, val):
|
||||
self.widget.where = val
|
||||
|
||||
def get_regex(self, state):
|
||||
raw = state['find']
|
||||
if state['mode'] != 'regex':
|
||||
raw = regex.escape(raw, special_only=True)
|
||||
flags = REGEX_FLAGS
|
||||
if not state['case_sensitive']:
|
||||
flags |= regex.IGNORECASE
|
||||
if state['mode'] == 'regex' and state['dot_all']:
|
||||
flags |= regex.DOTALL
|
||||
if state['direction'] == 'up':
|
||||
flags |= regex.REVERSE
|
||||
ans = regex_cache.get((flags, raw), None)
|
||||
if ans is None:
|
||||
ans = regex_cache[(flags, raw)] = regex.compile(raw, flags=flags)
|
||||
return ans
|
||||
|
||||
@ -20,6 +20,7 @@ from calibre.gui2.tweak_book.job import BlockingJob
|
||||
from calibre.gui2.tweak_book.boss import Boss
|
||||
from calibre.gui2.tweak_book.keyboard import KeyboardManager
|
||||
from calibre.gui2.tweak_book.preview import Preview
|
||||
from calibre.gui2.tweak_book.search import SearchPanel
|
||||
|
||||
class Central(QStackedWidget):
|
||||
|
||||
@ -56,6 +57,9 @@ class Central(QStackedWidget):
|
||||
self.modified_icon = QIcon(I('modified.png'))
|
||||
self.editor_tabs.currentChanged.connect(self.current_editor_changed)
|
||||
self.editor_tabs.tabCloseRequested.connect(self._close_requested)
|
||||
self.search_panel = SearchPanel(self)
|
||||
l.addWidget(self.search_panel)
|
||||
self.restore_state()
|
||||
|
||||
def _close_requested(self, index):
|
||||
editor = self.editor_tabs.widget(index)
|
||||
@ -91,6 +95,17 @@ class Central(QStackedWidget):
|
||||
def current_editor(self):
|
||||
return self.editor_tabs.currentWidget()
|
||||
|
||||
def save_state(self):
|
||||
tprefs.set('search-panel-visible', self.search_panel.isVisible())
|
||||
self.search_panel.save_state()
|
||||
|
||||
def restore_state(self):
|
||||
self.search_panel.setVisible(tprefs.get('search-panel-visible', False))
|
||||
self.search_panel.restore_state()
|
||||
|
||||
def show_find(self):
|
||||
self.search_panel.show_panel()
|
||||
|
||||
class Main(MainWindow):
|
||||
|
||||
APP_NAME = _('Tweak Book')
|
||||
@ -108,6 +123,9 @@ class Main(MainWindow):
|
||||
self.blocking_job = BlockingJob(self)
|
||||
self.keyboard = KeyboardManager()
|
||||
|
||||
self.central = Central(self)
|
||||
self.setCentralWidget(self.central)
|
||||
|
||||
self.create_actions()
|
||||
self.create_toolbars()
|
||||
self.create_docks()
|
||||
@ -120,9 +138,6 @@ class Main(MainWindow):
|
||||
f.setBold(True)
|
||||
self.status_bar.setFont(f)
|
||||
|
||||
self.central = Central(self)
|
||||
self.setCentralWidget(self.central)
|
||||
|
||||
self.boss(self)
|
||||
g = QApplication.instance().desktop().availableGeometry(self)
|
||||
self.resize(g.width()-50, g.height()-50)
|
||||
@ -139,7 +154,7 @@ class Main(MainWindow):
|
||||
group = _('Global Actions')
|
||||
|
||||
def reg(icon, text, target, sid, keys, description):
|
||||
ac = actions[sid] = QAction(QIcon(I(icon)), text, self)
|
||||
ac = actions[sid] = QAction(QIcon(I(icon)), text, self) if icon else QAction(text, self)
|
||||
ac.setObjectName('action-' + sid)
|
||||
if target is not None:
|
||||
ac.triggered.connect(target)
|
||||
@ -197,7 +212,28 @@ class Main(MainWindow):
|
||||
# Preview actions
|
||||
group = _('Preview')
|
||||
self.action_auto_reload_preview = reg('auto-reload.png', _('Auto reload preview'), None, 'auto-reload-preview', (), _('Auto reload preview'))
|
||||
self.action_reload_preview = reg('view-refresh.png', _('Refresh preview'), None, 'reload-preview', ('F5', 'Ctrl+R'), _('Refresh preview'))
|
||||
self.action_reload_preview = reg('view-refresh.png', _('Refresh preview'), None, 'reload-preview', ('F5',), _('Refresh preview'))
|
||||
|
||||
# Search actions
|
||||
group = _('Search')
|
||||
self.action_find = reg('search.png', _('&Find/Replace'), self.central.show_find, 'find-replace', ('Ctrl+F',), _('Show the Find/Replace panel'))
|
||||
def sreg(name, text, action, overrides={}, keys=(), description=None, icon=None):
|
||||
return reg(icon, text, partial(self.boss.search, action, overrides), name, keys, description or text.replace('&', ''))
|
||||
self.action_find_next = sreg('find-next', _('Find &Next'),
|
||||
'find', {'direction':'down'}, ('F3', 'Ctrl+G'), _('Find next match'))
|
||||
self.action_find_previous = sreg('find-previous', _('Find &Previous'),
|
||||
'find', {'direction':'up'}, ('Shift+F3', 'Shift+Ctrl+G'), _('Find previous match'))
|
||||
self.action_replace = sreg('replace', _('Replace'),
|
||||
'replace', keys=('Ctrl+R'), description=_('Replace current match'))
|
||||
self.action_replace_next = sreg('replace-next', _('&Replace and find next'),
|
||||
'replace-find', {'direction':'down'}, ('Ctrl+]'), _('Replace current match and find next'))
|
||||
self.action_replace_previous = sreg('replace-previous', _('R&eplace and find previous'),
|
||||
'replace-find', {'direction':'up'}, ('Ctrl+['), _('Replace current match and find previous'))
|
||||
self.action_replace_all = sreg('replace-all', _('Replace &all'),
|
||||
'replace-all', keys=('Ctrl+A'), description=_('Replace all matches'))
|
||||
self.action_count = sreg('count-matches', _('&Count all'),
|
||||
'count', keys=('Ctrl+N'), description=_('Count number of matches'))
|
||||
self.action_mark = reg(None, _('&Mark selected text'), self.boss.mark_selected_text, 'mark-selected-text', ('Ctrl+Shift+M',), _('Mark selected text'))
|
||||
|
||||
def create_menubar(self):
|
||||
b = self.menuBar()
|
||||
@ -233,6 +269,22 @@ class Main(MainWindow):
|
||||
elif name.endswith('-bar'):
|
||||
t.addAction(ac)
|
||||
|
||||
e = b.addMenu(_('&Search'))
|
||||
a = e.addAction
|
||||
a(self.action_find)
|
||||
e.addSeparator()
|
||||
a(self.action_find_next)
|
||||
a(self.action_find_previous)
|
||||
e.addSeparator()
|
||||
a(self.action_replace)
|
||||
a(self.action_replace_next)
|
||||
a(self.action_replace_previous)
|
||||
a(self.action_replace_all)
|
||||
e.addSeparator()
|
||||
a(self.action_count)
|
||||
e.addSeparator()
|
||||
a(self.action_mark)
|
||||
|
||||
def create_toolbars(self):
|
||||
def create(text, name):
|
||||
name += '-bar'
|
||||
@ -303,6 +355,7 @@ class Main(MainWindow):
|
||||
def save_state(self):
|
||||
tprefs.set('main_window_geometry', bytearray(self.saveGeometry()))
|
||||
tprefs.set('main_window_state', bytearray(self.saveState(self.STATE_VERSION)))
|
||||
self.central.save_state()
|
||||
|
||||
def restore_state(self):
|
||||
geom = tprefs.get('main_window_geometry', None)
|
||||
@ -311,6 +364,7 @@ class Main(MainWindow):
|
||||
state = tprefs.get('main_window_state', None)
|
||||
if state is not None:
|
||||
self.restoreState(state, self.STATE_VERSION)
|
||||
self.central.restore_state()
|
||||
# We never want to start with the inspector showing
|
||||
self.inspector_dock.close()
|
||||
|
||||
|
||||
@ -18,7 +18,7 @@ from calibre.gui2.viewer.toc import TOC
|
||||
from calibre.gui2.widgets import ProgressIndicator
|
||||
from calibre.gui2.main_window import MainWindow
|
||||
from calibre.gui2 import (Application, ORG_NAME, APP_UID, choose_files,
|
||||
info_dialog, error_dialog, open_url, available_height)
|
||||
info_dialog, error_dialog, open_url, available_height, setup_gui_option_parser, detach_gui)
|
||||
from calibre.ebooks.oeb.iterator.book import EbookIterator
|
||||
from calibre.ebooks import DRMError
|
||||
from calibre.constants import islinux, filesystem_encoding
|
||||
@ -1183,11 +1183,13 @@ def config(defaults=None):
|
||||
|
||||
def option_parser():
|
||||
c = config()
|
||||
return c.option_parser(usage=_('''\
|
||||
parser = c.option_parser(usage=_('''\
|
||||
%prog [options] file
|
||||
|
||||
View an ebook.
|
||||
'''))
|
||||
setup_gui_option_parser(parser)
|
||||
return parser
|
||||
|
||||
|
||||
def main(args=sys.argv):
|
||||
@ -1197,6 +1199,8 @@ def main(args=sys.argv):
|
||||
|
||||
parser = option_parser()
|
||||
opts, args = parser.parse_args(args)
|
||||
if getattr(opts, 'detach', False):
|
||||
detach_gui()
|
||||
try:
|
||||
open_at = float(opts.open_at)
|
||||
except:
|
||||
|
||||
@ -15,6 +15,12 @@ Test a binary calibre build to ensure that all needed binary images/libraries ha
|
||||
import cStringIO
|
||||
from calibre.constants import plugins, iswindows
|
||||
|
||||
def test_regex():
|
||||
import regex
|
||||
if regex.findall(r'(?i)(a)(b)', 'ab cd AB 1a1b') != [('a', 'b'), ('A', 'B')]:
|
||||
raise ValueError('regex module failed on a simple search')
|
||||
print ('regex OK!')
|
||||
|
||||
def test_html5lib():
|
||||
import html5lib.html5parser # noqa
|
||||
from html5lib import parse # noqa
|
||||
@ -119,6 +125,7 @@ def test():
|
||||
test_woff()
|
||||
test_qt()
|
||||
test_html5lib()
|
||||
test_regex()
|
||||
if iswindows:
|
||||
test_winutil()
|
||||
test_wpd()
|
||||
|
||||
@ -69,6 +69,7 @@ local_tz = _local_tz = SafeLocalTimeZone()
|
||||
|
||||
UNDEFINED_DATE = datetime(101,1,1, tzinfo=utc_tz)
|
||||
DEFAULT_DATE = datetime(2000,1,1, tzinfo=utc_tz)
|
||||
EPOCH = datetime(1970, 1, 1, tzinfo=_utc_tz)
|
||||
|
||||
def is_date_undefined(qt_or_dt):
|
||||
d = qt_or_dt
|
||||
@ -210,15 +211,23 @@ def now():
|
||||
def utcnow():
|
||||
return datetime.utcnow().replace(tzinfo=_utc_tz)
|
||||
|
||||
|
||||
def utcfromtimestamp(stamp):
|
||||
try:
|
||||
return datetime.utcfromtimestamp(stamp).replace(tzinfo=_utc_tz)
|
||||
except ValueError:
|
||||
# Raised if stamp if out of range for the platforms gmtime function
|
||||
# We print the error for debugging, but otherwise ignore it
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return utcnow()
|
||||
# Raised if stamp is out of range for the platforms gmtime function
|
||||
# For example, this happens with negative values on windows
|
||||
try:
|
||||
return EPOCH + timedelta(seconds=stamp)
|
||||
except (ValueError, OverflowError):
|
||||
# datetime can only represent years between 1 and 9999
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return utcnow()
|
||||
|
||||
def timestampfromdt(dt, assume_utc=True):
|
||||
return (as_utc(dt, assume_utc=assume_utc) - EPOCH).total_seconds()
|
||||
|
||||
# Format date functions
|
||||
|
||||
|
||||
15
src/calibre/utils/file_associations.py
Normal file
15
src/calibre/utils/file_associations.py
Normal file
@ -0,0 +1,15 @@
|
||||
#!/usr/bin/env python
|
||||
# vim:fileencoding=utf-8
|
||||
from __future__ import (unicode_literals, division, absolute_import,
|
||||
print_function)
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
|
||||
def file_assoc_windows(ft):
|
||||
# See the IQueryAssociations::GetString method documentation on MSDN
|
||||
from win32com.shell import shell, shellcon
|
||||
a = shell.AssocCreate()
|
||||
a.Init(0, '.' + ft.lower())
|
||||
return a.GetString(0, shellcon.ASSOCSTR_EXECUTABLE)
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
#!/usr/bin/env python
|
||||
# coding: utf-8
|
||||
# vim:fileencoding=utf-8
|
||||
|
||||
'''
|
||||
Created on 13 Jan 2011
|
||||
@ -135,6 +135,7 @@ class FormatterFunction(object):
|
||||
return unicode(ret)
|
||||
|
||||
class BuiltinFormatterFunction(FormatterFunction):
|
||||
|
||||
def __init__(self):
|
||||
formatter_functions().register_builtin(self)
|
||||
eval_func = inspect.getmembers(self.__class__,
|
||||
@ -355,7 +356,7 @@ class BuiltinLookup(BuiltinFormatterFunction):
|
||||
'variable save paths')
|
||||
|
||||
def evaluate(self, formatter, kwargs, mi, locals, val, *args):
|
||||
if len(args) == 2: # here for backwards compatibility
|
||||
if len(args) == 2: # here for backwards compatibility
|
||||
if val:
|
||||
return formatter.vformat('{'+args[0].strip()+'}', [], kwargs)
|
||||
else:
|
||||
@ -744,11 +745,11 @@ class BuiltinFormatNumber(BuiltinFormatterFunction):
|
||||
v1 = float(val)
|
||||
except:
|
||||
return ''
|
||||
try: # Try formatting the value as a float
|
||||
try: # Try formatting the value as a float
|
||||
return template.format(v1)
|
||||
except:
|
||||
pass
|
||||
try: # Try formatting the value as an int
|
||||
try: # Try formatting the value as an int
|
||||
v2 = trunc(v1)
|
||||
if v2 == v1:
|
||||
return template.format(v2)
|
||||
@ -1292,11 +1293,11 @@ class BuiltinTransliterate(BuiltinFormatterFunction):
|
||||
name = 'transliterate'
|
||||
arg_count = 1
|
||||
category = 'String manipulation'
|
||||
__doc__ = doc = _('transliterate(a) -- Returns a string in a latin alphabet '
|
||||
'formed by approximating the sound of the words in the '
|
||||
'source string. For example, if the source is "Фёдор '
|
||||
'Миха́йлович Достоевский" the function returns "Fiodor '
|
||||
'Mikhailovich Dostoievskii".')
|
||||
__doc__ = doc = _(u'transliterate(a) -- Returns a string in a latin alphabet '
|
||||
u'formed by approximating the sound of the words in the '
|
||||
u'source string. For example, if the source is "Фёдор '
|
||||
u'Миха́йлович Достоевский" the function returns "Fiodor '
|
||||
u'Mikhailovich Dostoievskii".')
|
||||
|
||||
def evaluate(self, formatter, kwargs, mi, locals, source):
|
||||
from calibre.utils.filenames import ascii_text
|
||||
@ -1329,6 +1330,7 @@ _formatter_builtins = [
|
||||
]
|
||||
|
||||
class FormatterUserFunction(FormatterFunction):
|
||||
|
||||
def __init__(self, name, doc, arg_count, program_text):
|
||||
self.name = name
|
||||
self.doc = doc
|
||||
@ -1338,9 +1340,9 @@ class FormatterUserFunction(FormatterFunction):
|
||||
tabs = re.compile(r'^\t*')
|
||||
def compile_user_function(name, doc, arg_count, eval_func):
|
||||
def replace_func(mo):
|
||||
return mo.group().replace('\t', ' ')
|
||||
return mo.group().replace('\t', ' ')
|
||||
|
||||
func = ' ' + '\n '.join([tabs.sub(replace_func, line )
|
||||
func = ' ' + '\n '.join([tabs.sub(replace_func, line)
|
||||
for line in eval_func.splitlines()])
|
||||
prog = '''
|
||||
from calibre.utils.formatter_functions import FormatterUserFunction
|
||||
|
||||
@ -78,7 +78,6 @@ class Article(object):
|
||||
self._title = clean_ascii_chars(val)
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
|
||||
def __repr__(self):
|
||||
return \
|
||||
(u'''\
|
||||
@ -97,7 +96,7 @@ Has content : %s
|
||||
return repr(self)
|
||||
|
||||
def is_same_as(self, other_article):
|
||||
#if self.title != getattr(other_article, 'title', False):
|
||||
# if self.title != getattr(other_article, 'title', False):
|
||||
# return False
|
||||
if self.url:
|
||||
return self.url == getattr(other_article, 'url', False)
|
||||
@ -137,7 +136,6 @@ class Feed(object):
|
||||
break
|
||||
self.parse_article(item)
|
||||
|
||||
|
||||
def populate_from_preparsed_feed(self, title, articles, oldest_article=7,
|
||||
max_articles_per_feed=100):
|
||||
self.title = unicode(title if title else _('Unknown feed'))
|
||||
@ -176,7 +174,6 @@ class Feed(object):
|
||||
d = item.get('date', '')
|
||||
article.formatted_date = d
|
||||
|
||||
|
||||
def parse_article(self, item):
|
||||
self.id_counter += 1
|
||||
id = item.get('id', None)
|
||||
@ -219,7 +216,8 @@ class Feed(object):
|
||||
self.articles.append(article)
|
||||
else:
|
||||
try:
|
||||
self.logger.debug('Skipping article %s (%s) from feed %s as it is too old.'%(title, article.localtime.strftime('%a, %d %b, %Y %H:%M'), self.title))
|
||||
self.logger.debug('Skipping article %s (%s) from feed %s as it is too old.'%
|
||||
(title, article.localtime.strftime('%a, %d %b, %Y %H:%M'), self.title))
|
||||
except UnicodeDecodeError:
|
||||
if not isinstance(title, unicode):
|
||||
title = title.decode('utf-8', 'replace')
|
||||
@ -310,7 +308,7 @@ class FeedCollection(list):
|
||||
self.duplicates = duplicates
|
||||
print len(duplicates)
|
||||
print map(len, self)
|
||||
#raise
|
||||
# raise
|
||||
|
||||
def find_article(self, article):
|
||||
for j, f in enumerate(self):
|
||||
|
||||
5
src/regex/README
Normal file
5
src/regex/README
Normal file
@ -0,0 +1,5 @@
|
||||
This regex engine is taken, with thanks, from: https://code.google.com/p/mrab-regex-hg/
|
||||
|
||||
It is licensed under the Python Software Foundation License
|
||||
|
||||
Author: Matthew Barnett
|
||||
678
src/regex/__init__.py
Normal file
678
src/regex/__init__.py
Normal file
@ -0,0 +1,678 @@
|
||||
#
|
||||
# Secret Labs' Regular Expression Engine
|
||||
#
|
||||
# Copyright (c) 1998-2001 by Secret Labs AB. All rights reserved.
|
||||
#
|
||||
# This version of the SRE library can be redistributed under CNRI's
|
||||
# Python 1.6 license. For any other use, please contact Secret Labs
|
||||
# AB (info@pythonware.com).
|
||||
#
|
||||
# Portions of this engine have been developed in cooperation with
|
||||
# CNRI. Hewlett-Packard provided funding for 1.6 integration and
|
||||
# other compatibility work.
|
||||
#
|
||||
# 2010-01-16 mrab Python front-end re-written and extended
|
||||
|
||||
r"""Support for regular expressions (RE).
|
||||
|
||||
This module provides regular expression matching operations similar to those
|
||||
found in Perl. It supports both 8-bit and Unicode strings; both the pattern and
|
||||
the strings being processed can contain null bytes and characters outside the
|
||||
US ASCII range.
|
||||
|
||||
Regular expressions can contain both special and ordinary characters. Most
|
||||
ordinary characters, like "A", "a", or "0", are the simplest regular
|
||||
expressions; they simply match themselves. You can concatenate ordinary
|
||||
characters, so last matches the string 'last'.
|
||||
|
||||
There are a few differences between the old (legacy) behaviour and the new
|
||||
(enhanced) behaviour, which are indicated by VERSION0 or VERSION1.
|
||||
|
||||
The special characters are:
|
||||
"." Matches any character except a newline.
|
||||
"^" Matches the start of the string.
|
||||
"$" Matches the end of the string or just before the
|
||||
newline at the end of the string.
|
||||
"*" Matches 0 or more (greedy) repetitions of the preceding
|
||||
RE. Greedy means that it will match as many repetitions
|
||||
as possible.
|
||||
"+" Matches 1 or more (greedy) repetitions of the preceding
|
||||
RE.
|
||||
"?" Matches 0 or 1 (greedy) of the preceding RE.
|
||||
*?,+?,?? Non-greedy versions of the previous three special
|
||||
characters.
|
||||
*+,++,?+ Possessive versions of the previous three special
|
||||
characters.
|
||||
{m,n} Matches from m to n repetitions of the preceding RE.
|
||||
{m,n}? Non-greedy version of the above.
|
||||
{m,n}+ Possessive version of the above.
|
||||
{...} Fuzzy matching constraints.
|
||||
"\\" Either escapes special characters or signals a special
|
||||
sequence.
|
||||
[...] Indicates a set of characters. A "^" as the first
|
||||
character indicates a complementing set.
|
||||
"|" A|B, creates an RE that will match either A or B.
|
||||
(...) Matches the RE inside the parentheses. The contents are
|
||||
captured and can be retrieved or matched later in the
|
||||
string.
|
||||
(?flags-flags) VERSION1: Sets/clears the flags for the remainder of
|
||||
the group or pattern; VERSION0: Sets the flags for the
|
||||
entire pattern.
|
||||
(?:...) Non-capturing version of regular parentheses.
|
||||
(?>...) Atomic non-capturing version of regular parentheses.
|
||||
(?flags-flags:...) Non-capturing version of regular parentheses with local
|
||||
flags.
|
||||
(?P<name>...) The substring matched by the group is accessible by
|
||||
name.
|
||||
(?<name>...) The substring matched by the group is accessible by
|
||||
name.
|
||||
(?P=name) Matches the text matched earlier by the group named
|
||||
name.
|
||||
(?#...) A comment; ignored.
|
||||
(?=...) Matches if ... matches next, but doesn't consume the
|
||||
string.
|
||||
(?!...) Matches if ... doesn't match next.
|
||||
(?<=...) Matches if preceded by ....
|
||||
(?<!...) Matches if not preceded by ....
|
||||
(?(id)yes|no) Matches yes pattern if group id matched, the (optional)
|
||||
no pattern otherwise.
|
||||
(?|...|...) (?|A|B), creates an RE that will match either A or B,
|
||||
but reuses capture group numbers across the
|
||||
alternatives.
|
||||
|
||||
The fuzzy matching constraints are: "i" to permit insertions, "d" to permit
|
||||
deletions, "s" to permit substitutions, "e" to permit any of these. Limits are
|
||||
optional with "<=" and "<". If any type of error is provided then any type not
|
||||
provided is not permitted.
|
||||
|
||||
A cost equation may be provided.
|
||||
|
||||
Examples:
|
||||
(?:fuzzy){i<=2}
|
||||
(?:fuzzy){i<=1,s<=2,d<=1,1i+1s+1d<3}
|
||||
|
||||
VERSION1: Set operators are supported, and a set can include nested sets. The
|
||||
set operators, in order of increasing precedence, are:
|
||||
|| Set union ("x||y" means "x or y").
|
||||
~~ (double tilde) Symmetric set difference ("x~~y" means "x or y, but not
|
||||
both").
|
||||
&& Set intersection ("x&&y" means "x and y").
|
||||
-- (double dash) Set difference ("x--y" means "x but not y").
|
||||
|
||||
Implicit union, ie, simple juxtaposition like in [ab], has the highest
|
||||
precedence.
|
||||
|
||||
VERSION0 and VERSION1:
|
||||
The special sequences consist of "\\" and a character from the list below. If
|
||||
the ordinary character is not on the list, then the resulting RE will match the
|
||||
second character.
|
||||
\number Matches the contents of the group of the same number if
|
||||
number is no more than 2 digits, otherwise the character
|
||||
with the 3-digit octal code.
|
||||
\a Matches the bell character.
|
||||
\A Matches only at the start of the string.
|
||||
\b Matches the empty string, but only at the start or end of a
|
||||
word.
|
||||
\B Matches the empty string, but not at the start or end of a
|
||||
word.
|
||||
\d Matches any decimal digit; equivalent to the set [0-9] when
|
||||
matching a bytestring or a Unicode string with the ASCII
|
||||
flag, or the whole range of Unicode digits when matching a
|
||||
Unicode string.
|
||||
\D Matches any non-digit character; equivalent to [^\d].
|
||||
\f Matches the formfeed character.
|
||||
\g<name> Matches the text matched by the group named name.
|
||||
\G Matches the empty string, but only at the position where
|
||||
the search started.
|
||||
\L<name> Named list. The list is provided as a keyword argument.
|
||||
\m Matches the empty string, but only at the start of a word.
|
||||
\M Matches the empty string, but only at the end of a word.
|
||||
\n Matches the newline character.
|
||||
\N{name} Matches the named character.
|
||||
\p{name=value} Matches the character if its property has the specified
|
||||
value.
|
||||
\P{name=value} Matches the character if its property hasn't the specified
|
||||
value.
|
||||
\r Matches the carriage-return character.
|
||||
\s Matches any whitespace character; equivalent to
|
||||
[ \t\n\r\f\v].
|
||||
\S Matches any non-whitespace character; equivalent to [^\s].
|
||||
\t Matches the tab character.
|
||||
\uXXXX Matches the Unicode codepoint with 4-digit hex code XXXX.
|
||||
\UXXXXXXXX Matches the Unicode codepoint with 8-digit hex code
|
||||
XXXXXXXX.
|
||||
\v Matches the vertical tab character.
|
||||
\w Matches any alphanumeric character; equivalent to
|
||||
[a-zA-Z0-9_] when matching a bytestring or a Unicode string
|
||||
with the ASCII flag, or the whole range of Unicode
|
||||
alphanumeric characters (letters plus digits plus
|
||||
underscore) when matching a Unicode string. With LOCALE, it
|
||||
will match the set [0-9_] plus characters defined as
|
||||
letters for the current locale.
|
||||
\W Matches the complement of \w; equivalent to [^\w].
|
||||
\xXX Matches the character with 2-digit hex code XX.
|
||||
\X Matches a grapheme.
|
||||
\Z Matches only at the end of the string.
|
||||
\\ Matches a literal backslash.
|
||||
|
||||
This module exports the following functions:
|
||||
match Match a regular expression pattern at the beginning of a string.
|
||||
fullmatch Match a regular expression pattern against all of a string.
|
||||
search Search a string for the presence of a pattern.
|
||||
sub Substitute occurrences of a pattern found in a string using a
|
||||
template string.
|
||||
subf Substitute occurrences of a pattern found in a string using a
|
||||
format string.
|
||||
subn Same as sub, but also return the number of substitutions made.
|
||||
subfn Same as subf, but also return the number of substitutions made.
|
||||
split Split a string by the occurrences of a pattern. VERSION1: will
|
||||
split at zero-width match; VERSION0: won't split at zero-width
|
||||
match.
|
||||
splititer Return an iterator yielding the parts of a split string.
|
||||
findall Find all occurrences of a pattern in a string.
|
||||
finditer Return an iterator yielding a match object for each match.
|
||||
compile Compile a pattern into a Pattern object.
|
||||
purge Clear the regular expression cache.
|
||||
escape Backslash all non-alphanumerics or special characters in a
|
||||
string.
|
||||
|
||||
Most of the functions support a concurrent parameter: if True, the GIL will be
|
||||
released during matching, allowing other Python threads to run concurrently. If
|
||||
the string changes during matching, the behaviour is undefined. This parameter
|
||||
is not needed when working on the builtin (immutable) string classes.
|
||||
|
||||
Some of the functions in this module take flags as optional parameters. Most of
|
||||
these flags can also be set within an RE:
|
||||
A a ASCII Make \w, \W, \b, \B, \d, and \D match the
|
||||
corresponding ASCII character categories. Default
|
||||
when matching a bytestring.
|
||||
B b BESTMATCH Find the best fuzzy match (default is first).
|
||||
D DEBUG Print the parsed pattern.
|
||||
F f FULLCASE Use full case-folding when performing
|
||||
case-insensitive matching in Unicode.
|
||||
I i IGNORECASE Perform case-insensitive matching.
|
||||
L L LOCALE Make \w, \W, \b, \B, \d, and \D dependent on the
|
||||
current locale. (One byte per character only.)
|
||||
M m MULTILINE "^" matches the beginning of lines (after a newline)
|
||||
as well as the string. "$" matches the end of lines
|
||||
(before a newline) as well as the end of the string.
|
||||
E e ENHANCEMATCH Attempt to improve the fit after finding the first
|
||||
fuzzy match.
|
||||
R r REVERSE Searches backwards.
|
||||
S s DOTALL "." matches any character at all, including the
|
||||
newline.
|
||||
U u UNICODE Make \w, \W, \b, \B, \d, and \D dependent on the
|
||||
Unicode locale. Default when matching a Unicode
|
||||
string.
|
||||
V0 V0 VERSION0 Turn on the old legacy behaviour.
|
||||
V1 V1 VERSION1 Turn on the new enhanced behaviour. This flag
|
||||
includes the FULLCASE flag.
|
||||
W w WORD Make \b and \B work with default Unicode word breaks
|
||||
and make ".", "^" and "$" work with Unicode line
|
||||
breaks.
|
||||
X x VERBOSE Ignore whitespace and comments for nicer looking REs.
|
||||
|
||||
This module also defines an exception 'error'.
|
||||
|
||||
"""
|
||||
|
||||
# Public symbols.
|
||||
__all__ = ["compile", "escape", "findall", "finditer", "fullmatch", "match",
|
||||
"purge", "search", "split", "splititer", "sub", "subf", "subfn", "subn",
|
||||
"template", "Scanner", "A", "ASCII", "B", "BESTMATCH", "D", "DEBUG", "E",
|
||||
"ENHANCEMATCH", "S", "DOTALL", "F", "FULLCASE", "I", "IGNORECASE", "L",
|
||||
"LOCALE", "M", "MULTILINE", "R", "REVERSE", "T", "TEMPLATE", "U", "UNICODE",
|
||||
"V0", "VERSION0", "V1", "VERSION1", "X", "VERBOSE", "W", "WORD", "error",
|
||||
"Regex"]
|
||||
|
||||
__version__ = "2.4.35"
|
||||
|
||||
# --------------------------------------------------------------------
|
||||
# Public interface.
|
||||
|
||||
def match(pattern, string, flags=0, pos=None, endpos=None, concurrent=None,
|
||||
**kwargs):
|
||||
"""Try to apply the pattern at the start of the string, returning a match
|
||||
object, or None if no match was found."""
|
||||
return _compile(pattern, flags, kwargs).match(string, pos, endpos,
|
||||
concurrent)
|
||||
|
||||
def fullmatch(pattern, string, flags=0, pos=None, endpos=None, concurrent=None,
|
||||
**kwargs):
|
||||
"""Try to apply the pattern against all of the string, returning a match
|
||||
object, or None if no match was found."""
|
||||
return _compile(pattern, flags, kwargs).fullmatch(string, pos, endpos,
|
||||
concurrent)
|
||||
|
||||
def search(pattern, string, flags=0, pos=None, endpos=None, concurrent=None,
|
||||
**kwargs):
|
||||
"""Search through string looking for a match to the pattern, returning a
|
||||
match object, or None if no match was found."""
|
||||
return _compile(pattern, flags, kwargs).search(string, pos, endpos,
|
||||
concurrent)
|
||||
|
||||
def sub(pattern, repl, string, count=0, flags=0, pos=None, endpos=None,
|
||||
concurrent=None, **kwargs):
|
||||
"""Return the string obtained by replacing the leftmost (or rightmost with a
|
||||
reverse pattern) non-overlapping occurrences of the pattern in string by the
|
||||
replacement repl. repl can be either a string or a callable; if a string,
|
||||
backslash escapes in it are processed; if a callable, it's passed the match
|
||||
object and must return a replacement string to be used."""
|
||||
return _compile(pattern, flags, kwargs).sub(repl, string, count, pos,
|
||||
endpos, concurrent)
|
||||
|
||||
def subf(pattern, format, string, count=0, flags=0, pos=None, endpos=None,
|
||||
concurrent=None, **kwargs):
|
||||
"""Return the string obtained by replacing the leftmost (or rightmost with a
|
||||
reverse pattern) non-overlapping occurrences of the pattern in string by the
|
||||
replacement format. format can be either a string or a callable; if a string,
|
||||
it's treated as a format string; if a callable, it's passed the match object
|
||||
and must return a replacement string to be used."""
|
||||
return _compile(pattern, flags, kwargs).subf(format, string, count, pos,
|
||||
endpos, concurrent)
|
||||
|
||||
def subn(pattern, repl, string, count=0, flags=0, pos=None, endpos=None,
|
||||
concurrent=None, **kwargs):
|
||||
"""Return a 2-tuple containing (new_string, number). new_string is the string
|
||||
obtained by replacing the leftmost (or rightmost with a reverse pattern)
|
||||
non-overlapping occurrences of the pattern in the source string by the
|
||||
replacement repl. number is the number of substitutions that were made. repl
|
||||
can be either a string or a callable; if a string, backslash escapes in it
|
||||
are processed; if a callable, it's passed the match object and must return a
|
||||
replacement string to be used."""
|
||||
return _compile(pattern, flags, kwargs).subn(repl, string, count, pos,
|
||||
endpos, concurrent)
|
||||
|
||||
def subfn(pattern, format, string, count=0, flags=0, pos=None, endpos=None,
|
||||
concurrent=None, **kwargs):
|
||||
"""Return a 2-tuple containing (new_string, number). new_string is the string
|
||||
obtained by replacing the leftmost (or rightmost with a reverse pattern)
|
||||
non-overlapping occurrences of the pattern in the source string by the
|
||||
replacement format. number is the number of substitutions that were made. format
|
||||
can be either a string or a callable; if a string, it's treated as a format
|
||||
string; if a callable, it's passed the match object and must return a
|
||||
replacement string to be used."""
|
||||
return _compile(pattern, flags, kwargs).subfn(format, string, count, pos,
|
||||
endpos, concurrent)
|
||||
|
||||
def split(pattern, string, maxsplit=0, flags=0, concurrent=None, **kwargs):
|
||||
"""Split the source string by the occurrences of the pattern, returning a
|
||||
list containing the resulting substrings. If capturing parentheses are used
|
||||
in pattern, then the text of all groups in the pattern are also returned as
|
||||
part of the resulting list. If maxsplit is nonzero, at most maxsplit splits
|
||||
occur, and the remainder of the string is returned as the final element of
|
||||
the list."""
|
||||
return _compile(pattern, flags, kwargs).split(string, maxsplit, concurrent)
|
||||
|
||||
def splititer(pattern, string, maxsplit=0, flags=0, concurrent=None, **kwargs):
|
||||
"Return an iterator yielding the parts of a split string."
|
||||
return _compile(pattern, flags, kwargs).splititer(string, maxsplit,
|
||||
concurrent)
|
||||
|
||||
def findall(pattern, string, flags=0, pos=None, endpos=None, overlapped=False,
|
||||
concurrent=None, **kwargs):
|
||||
"""Return a list of all matches in the string. The matches may be overlapped
|
||||
if overlapped is True. If one or more groups are present in the pattern,
|
||||
return a list of groups; this will be a list of tuples if the pattern has
|
||||
more than one group. Empty matches are included in the result."""
|
||||
return _compile(pattern, flags, kwargs).findall(string, pos, endpos,
|
||||
overlapped, concurrent)
|
||||
|
||||
def finditer(pattern, string, flags=0, pos=None, endpos=None, overlapped=False,
|
||||
concurrent=None, **kwargs):
|
||||
"""Return an iterator over all matches in the string. The matches may be
|
||||
overlapped if overlapped is True. For each match, the iterator returns a
|
||||
match object. Empty matches are included in the result."""
|
||||
return _compile(pattern, flags, kwargs).finditer(string, pos, endpos,
|
||||
overlapped, concurrent)
|
||||
|
||||
def compile(pattern, flags=0, **kwargs):
|
||||
"Compile a regular expression pattern, returning a pattern object."
|
||||
return _compile(pattern, flags, kwargs)
|
||||
|
||||
def purge():
|
||||
"Clear the regular expression cache"
|
||||
_cache.clear()
|
||||
|
||||
def template(pattern, flags=0):
|
||||
"Compile a template pattern, returning a pattern object."
|
||||
return _compile(pattern, flags | TEMPLATE)
|
||||
|
||||
def escape(pattern, special_only=False):
|
||||
"Escape all non-alphanumeric characters or special characters in pattern."
|
||||
if isinstance(pattern, unicode):
|
||||
s = []
|
||||
if special_only:
|
||||
for c in pattern:
|
||||
if c in _METACHARS:
|
||||
s.append(u"\\")
|
||||
s.append(c)
|
||||
elif c == u"\x00":
|
||||
s.append(u"\\000")
|
||||
else:
|
||||
s.append(c)
|
||||
else:
|
||||
for c in pattern:
|
||||
if c in _ALNUM:
|
||||
s.append(c)
|
||||
elif c == u"\x00":
|
||||
s.append(u"\\000")
|
||||
else:
|
||||
s.append(u"\\")
|
||||
s.append(c)
|
||||
|
||||
return u"".join(s)
|
||||
else:
|
||||
s = []
|
||||
if special_only:
|
||||
for c in pattern:
|
||||
if c in _METACHARS:
|
||||
s.append("\\")
|
||||
s.append(c)
|
||||
elif c == "\x00":
|
||||
s.append("\\000")
|
||||
else:
|
||||
s.append(c)
|
||||
else:
|
||||
for c in pattern:
|
||||
if c in _ALNUM:
|
||||
s.append(c)
|
||||
elif c == "\x00":
|
||||
s.append("\\000")
|
||||
else:
|
||||
s.append("\\")
|
||||
s.append(c)
|
||||
|
||||
return "".join(s)
|
||||
|
||||
# --------------------------------------------------------------------
|
||||
# Internals.
|
||||
|
||||
from . import _regex_core
|
||||
from calibre.constants import plugins
|
||||
_regex = plugins['_regex'][0]
|
||||
from threading import RLock as _RLock
|
||||
from ._regex_core import *
|
||||
from ._regex_core import (_ALL_VERSIONS, _ALL_ENCODINGS, _FirstSetError,
|
||||
_UnscopedFlagSet, _check_group_features, _compile_firstset,
|
||||
_compile_replacement, _flatten_code, _fold_case, _get_required_string,
|
||||
_parse_pattern, _shrink_cache)
|
||||
from ._regex_core import (ALNUM as _ALNUM, Info as _Info, OP as _OP, Source as
|
||||
_Source, Fuzzy as _Fuzzy)
|
||||
|
||||
# Version 0 is the old behaviour, compatible with the original 're' module.
|
||||
# Version 1 is the new behaviour, which differs slightly.
|
||||
|
||||
DEFAULT_VERSION = VERSION0
|
||||
|
||||
_METACHARS = frozenset("()[]{}?*+|^$\\.")
|
||||
|
||||
_regex_core.DEFAULT_VERSION = DEFAULT_VERSION
|
||||
|
||||
# Caches for the patterns and replacements.
|
||||
_cache = {}
|
||||
_cache_lock = _RLock()
|
||||
_named_args = {}
|
||||
_replacement_cache = {}
|
||||
|
||||
# Maximum size of the cache.
|
||||
_MAXCACHE = 500
|
||||
_MAXREPCACHE = 500
|
||||
|
||||
def _compile(pattern, flags=0, kwargs={}):
|
||||
"Compiles a regular expression to a PatternObject."
|
||||
try:
|
||||
# Do we know what keyword arguments are needed?
|
||||
args_key = pattern, type(pattern), flags
|
||||
args_needed = _named_args[args_key]
|
||||
|
||||
# Are we being provided with its required keyword arguments?
|
||||
args_supplied = set()
|
||||
if args_needed:
|
||||
for k, v in args_needed:
|
||||
try:
|
||||
args_supplied.add((k, frozenset(kwargs[k])))
|
||||
except KeyError:
|
||||
raise error("missing named list")
|
||||
|
||||
args_supplied = frozenset(args_supplied)
|
||||
|
||||
# Have we already seen this regular expression and named list?
|
||||
pattern_key = (pattern, type(pattern), flags, args_supplied,
|
||||
DEFAULT_VERSION)
|
||||
return _cache[pattern_key]
|
||||
except KeyError:
|
||||
# It's a new pattern, or new named list for a known pattern.
|
||||
pass
|
||||
|
||||
# Guess the encoding from the class of the pattern string.
|
||||
if isinstance(pattern, unicode):
|
||||
guess_encoding = UNICODE
|
||||
elif isinstance(pattern, str):
|
||||
guess_encoding = ASCII
|
||||
elif isinstance(pattern, _pattern_type):
|
||||
if flags:
|
||||
raise ValueError("can't process flags argument with a compiled pattern")
|
||||
|
||||
return pattern
|
||||
else:
|
||||
raise TypeError("first argument must be a string or compiled pattern")
|
||||
|
||||
# Set the default version in the core code in case it has been changed.
|
||||
_regex_core.DEFAULT_VERSION = DEFAULT_VERSION
|
||||
|
||||
caught_exception = None
|
||||
|
||||
while True:
|
||||
try:
|
||||
source = _Source(pattern)
|
||||
info = _Info(flags, source.char_type, kwargs)
|
||||
info.guess_encoding = guess_encoding
|
||||
source.ignore_space = bool(info.flags & VERBOSE)
|
||||
parsed = _parse_pattern(source, info)
|
||||
break
|
||||
except _UnscopedFlagSet:
|
||||
# Remember the global flags for the next attempt.
|
||||
flags = info.global_flags
|
||||
except error, e:
|
||||
caught_exception = e
|
||||
|
||||
if caught_exception:
|
||||
raise error(str(caught_exception))
|
||||
|
||||
if not source.at_end():
|
||||
raise error("trailing characters in pattern at position %d" % source.pos)
|
||||
|
||||
# Check the global flags for conflicts.
|
||||
version = (info.flags & _ALL_VERSIONS) or DEFAULT_VERSION
|
||||
if version not in (0, VERSION0, VERSION1):
|
||||
raise ValueError("VERSION0 and VERSION1 flags are mutually incompatible")
|
||||
|
||||
if (info.flags & _ALL_ENCODINGS) not in (0, ASCII, LOCALE, UNICODE):
|
||||
raise ValueError("ASCII, LOCALE and UNICODE flags are mutually incompatible")
|
||||
|
||||
if not (info.flags & _ALL_ENCODINGS):
|
||||
if isinstance(pattern, unicode):
|
||||
info.flags |= UNICODE
|
||||
else:
|
||||
info.flags |= ASCII
|
||||
|
||||
reverse = bool(info.flags & REVERSE)
|
||||
fuzzy = isinstance(parsed, _Fuzzy)
|
||||
|
||||
# Should we print the parsed pattern?
|
||||
if flags & DEBUG:
|
||||
parsed.dump(indent=0, reverse=reverse)
|
||||
|
||||
# Fix the group references.
|
||||
parsed.fix_groups(reverse, False)
|
||||
|
||||
# Optimise the parsed pattern.
|
||||
parsed = parsed.optimise(info)
|
||||
parsed = parsed.pack_characters(info)
|
||||
|
||||
# Get the required string.
|
||||
req_offset, req_chars, req_flags = _get_required_string(parsed, info.flags)
|
||||
|
||||
# Build the named lists.
|
||||
named_lists = {}
|
||||
named_list_indexes = [None] * len(info.named_lists_used)
|
||||
args_needed = set()
|
||||
for key, index in info.named_lists_used.items():
|
||||
name, case_flags = key
|
||||
values = frozenset(kwargs[name])
|
||||
if case_flags:
|
||||
items = frozenset(_fold_case(info, v) for v in values)
|
||||
else:
|
||||
items = values
|
||||
named_lists[name] = values
|
||||
named_list_indexes[index] = items
|
||||
args_needed.add((name, values))
|
||||
|
||||
# Check the features of the groups.
|
||||
_check_group_features(info, parsed)
|
||||
|
||||
# Compile the parsed pattern. The result is a list of tuples.
|
||||
code = parsed.compile(reverse)
|
||||
|
||||
# Is there a group call to the pattern as a whole?
|
||||
key = (0, reverse, fuzzy)
|
||||
ref = info.call_refs.get(key)
|
||||
if ref is not None:
|
||||
code = [(_OP.CALL_REF, ref)] + code + [(_OP.END, )]
|
||||
|
||||
# Add the final 'success' opcode.
|
||||
code += [(_OP.SUCCESS, )]
|
||||
|
||||
# Compile the additional copies of the groups that we need.
|
||||
for group, rev, fuz in info.additional_groups:
|
||||
code += group.compile(rev, fuz)
|
||||
|
||||
# Flatten the code into a list of ints.
|
||||
code = _flatten_code(code)
|
||||
|
||||
if not parsed.has_simple_start():
|
||||
# Get the first set, if possible.
|
||||
try:
|
||||
fs_code = _compile_firstset(info, parsed.get_firstset(reverse))
|
||||
fs_code = _flatten_code(fs_code)
|
||||
code = fs_code + code
|
||||
except _FirstSetError:
|
||||
pass
|
||||
|
||||
# The named capture groups.
|
||||
index_group = dict((v, n) for n, v in info.group_index.items())
|
||||
|
||||
# Create the PatternObject.
|
||||
#
|
||||
# Local flags like IGNORECASE affect the code generation, but aren't needed
|
||||
# by the PatternObject itself. Conversely, global flags like LOCALE _don't_
|
||||
# affect the code generation but _are_ needed by the PatternObject.
|
||||
compiled_pattern = _regex.compile(pattern, info.flags | version, code,
|
||||
info.group_index, index_group, named_lists, named_list_indexes,
|
||||
req_offset, req_chars, req_flags, info.group_count)
|
||||
|
||||
# Do we need to reduce the size of the cache?
|
||||
if len(_cache) >= _MAXCACHE:
|
||||
_cache_lock.acquire()
|
||||
try:
|
||||
_shrink_cache(_cache, _named_args, _MAXCACHE)
|
||||
finally:
|
||||
_cache_lock.release()
|
||||
|
||||
args_needed = frozenset(args_needed)
|
||||
|
||||
# Store this regular expression and named list.
|
||||
pattern_key = (pattern, type(pattern), flags, args_needed, DEFAULT_VERSION)
|
||||
_cache[pattern_key] = compiled_pattern
|
||||
|
||||
# Store what keyword arguments are needed.
|
||||
_named_args[args_key] = args_needed
|
||||
|
||||
return compiled_pattern
|
||||
|
||||
def _compile_replacement_helper(pattern, template):
|
||||
"Compiles a replacement template."
|
||||
# This function is called by the _regex module.
|
||||
|
||||
# Have we seen this before?
|
||||
key = pattern.pattern, pattern.flags, template
|
||||
compiled = _replacement_cache.get(key)
|
||||
if compiled is not None:
|
||||
return compiled
|
||||
|
||||
if len(_replacement_cache) >= _MAXREPCACHE:
|
||||
_replacement_cache.clear()
|
||||
|
||||
is_unicode = isinstance(template, unicode)
|
||||
source = _Source(template)
|
||||
if is_unicode:
|
||||
def make_string(char_codes):
|
||||
return u"".join(unichr(c) for c in char_codes)
|
||||
else:
|
||||
def make_string(char_codes):
|
||||
return "".join(chr(c) for c in char_codes)
|
||||
|
||||
compiled = []
|
||||
literal = []
|
||||
while True:
|
||||
ch = source.get()
|
||||
if not ch:
|
||||
break
|
||||
if ch == "\\":
|
||||
# '_compile_replacement' will return either an int group reference
|
||||
# or a string literal. It returns items (plural) in order to handle
|
||||
# a 2-character literal (an invalid escape sequence).
|
||||
is_group, items = _compile_replacement(source, pattern, is_unicode)
|
||||
if is_group:
|
||||
# It's a group, so first flush the literal.
|
||||
if literal:
|
||||
compiled.append(make_string(literal))
|
||||
literal = []
|
||||
compiled.extend(items)
|
||||
else:
|
||||
literal.extend(items)
|
||||
else:
|
||||
literal.append(ord(ch))
|
||||
|
||||
# Flush the literal.
|
||||
if literal:
|
||||
compiled.append(make_string(literal))
|
||||
|
||||
_replacement_cache[key] = compiled
|
||||
|
||||
return compiled
|
||||
|
||||
# We define _pattern_type here after all the support objects have been defined.
|
||||
_pattern_type = type(_compile("", 0, {}))
|
||||
|
||||
# We'll define an alias for the 'compile' function so that the repr of a
|
||||
# pattern object is eval-able.
|
||||
Regex = compile
|
||||
|
||||
# Register myself for pickling.
|
||||
import copy_reg as _copy_reg
|
||||
|
||||
def _pickle(p):
|
||||
return _compile, (p.pattern, p.flags)
|
||||
|
||||
_copy_reg.pickle(_pattern_type, _pickle, _compile)
|
||||
|
||||
if not hasattr(str, "format"):
|
||||
# Strings don't have the .format method (below Python 2.6).
|
||||
while True:
|
||||
_start = __doc__.find(" subf")
|
||||
if _start < 0:
|
||||
break
|
||||
|
||||
_end = __doc__.find("\n", _start) + 1
|
||||
while __doc__.startswith(" ", _end):
|
||||
_end = __doc__.find("\n", _end) + 1
|
||||
|
||||
__doc__ = __doc__[ : _start] + __doc__[_end : ]
|
||||
|
||||
__all__ = [_name for _name in __all__ if not _name.startswith("subf")]
|
||||
|
||||
del _start, _end
|
||||
|
||||
del subf, subfn
|
||||
19957
src/regex/_regex.c
Normal file
19957
src/regex/_regex.c
Normal file
File diff suppressed because it is too large
Load Diff
228
src/regex/_regex.h
Normal file
228
src/regex/_regex.h
Normal file
@ -0,0 +1,228 @@
|
||||
/*
|
||||
* Secret Labs' Regular Expression Engine
|
||||
*
|
||||
* regular expression matching engine
|
||||
*
|
||||
* Copyright (c) 1997-2001 by Secret Labs AB. All rights reserved.
|
||||
*
|
||||
* NOTE: This file is generated by regex.py. If you need
|
||||
* to change anything in here, edit regex.py and run it.
|
||||
*
|
||||
* 2010-01-16 mrab Re-written
|
||||
*/
|
||||
|
||||
/* Supports Unicode version 6.3.0. */
|
||||
|
||||
#define RE_MAGIC 20100116
|
||||
|
||||
#include "_regex_unicode.h"
|
||||
|
||||
/* Operators. */
|
||||
#define RE_OP_FAILURE 0
|
||||
#define RE_OP_SUCCESS 1
|
||||
#define RE_OP_ANY 2
|
||||
#define RE_OP_ANY_ALL 3
|
||||
#define RE_OP_ANY_ALL_REV 4
|
||||
#define RE_OP_ANY_REV 5
|
||||
#define RE_OP_ANY_U 6
|
||||
#define RE_OP_ANY_U_REV 7
|
||||
#define RE_OP_ATOMIC 8
|
||||
#define RE_OP_BOUNDARY 9
|
||||
#define RE_OP_BRANCH 10
|
||||
#define RE_OP_CALL_REF 11
|
||||
#define RE_OP_CHARACTER 12
|
||||
#define RE_OP_CHARACTER_IGN 13
|
||||
#define RE_OP_CHARACTER_IGN_REV 14
|
||||
#define RE_OP_CHARACTER_REV 15
|
||||
#define RE_OP_DEFAULT_BOUNDARY 16
|
||||
#define RE_OP_DEFAULT_END_OF_WORD 17
|
||||
#define RE_OP_DEFAULT_START_OF_WORD 18
|
||||
#define RE_OP_END 19
|
||||
#define RE_OP_END_OF_LINE 20
|
||||
#define RE_OP_END_OF_LINE_U 21
|
||||
#define RE_OP_END_OF_STRING 22
|
||||
#define RE_OP_END_OF_STRING_LINE 23
|
||||
#define RE_OP_END_OF_STRING_LINE_U 24
|
||||
#define RE_OP_END_OF_WORD 25
|
||||
#define RE_OP_FUZZY 26
|
||||
#define RE_OP_GRAPHEME_BOUNDARY 27
|
||||
#define RE_OP_GREEDY_REPEAT 28
|
||||
#define RE_OP_GROUP 29
|
||||
#define RE_OP_GROUP_CALL 30
|
||||
#define RE_OP_GROUP_EXISTS 31
|
||||
#define RE_OP_LAZY_REPEAT 32
|
||||
#define RE_OP_LOOKAROUND 33
|
||||
#define RE_OP_NEXT 34
|
||||
#define RE_OP_PROPERTY 35
|
||||
#define RE_OP_PROPERTY_IGN 36
|
||||
#define RE_OP_PROPERTY_IGN_REV 37
|
||||
#define RE_OP_PROPERTY_REV 38
|
||||
#define RE_OP_RANGE 39
|
||||
#define RE_OP_RANGE_IGN 40
|
||||
#define RE_OP_RANGE_IGN_REV 41
|
||||
#define RE_OP_RANGE_REV 42
|
||||
#define RE_OP_REF_GROUP 43
|
||||
#define RE_OP_REF_GROUP_FLD 44
|
||||
#define RE_OP_REF_GROUP_FLD_REV 45
|
||||
#define RE_OP_REF_GROUP_IGN 46
|
||||
#define RE_OP_REF_GROUP_IGN_REV 47
|
||||
#define RE_OP_REF_GROUP_REV 48
|
||||
#define RE_OP_SEARCH_ANCHOR 49
|
||||
#define RE_OP_SET_DIFF 50
|
||||
#define RE_OP_SET_DIFF_IGN 51
|
||||
#define RE_OP_SET_DIFF_IGN_REV 52
|
||||
#define RE_OP_SET_DIFF_REV 53
|
||||
#define RE_OP_SET_INTER 54
|
||||
#define RE_OP_SET_INTER_IGN 55
|
||||
#define RE_OP_SET_INTER_IGN_REV 56
|
||||
#define RE_OP_SET_INTER_REV 57
|
||||
#define RE_OP_SET_SYM_DIFF 58
|
||||
#define RE_OP_SET_SYM_DIFF_IGN 59
|
||||
#define RE_OP_SET_SYM_DIFF_IGN_REV 60
|
||||
#define RE_OP_SET_SYM_DIFF_REV 61
|
||||
#define RE_OP_SET_UNION 62
|
||||
#define RE_OP_SET_UNION_IGN 63
|
||||
#define RE_OP_SET_UNION_IGN_REV 64
|
||||
#define RE_OP_SET_UNION_REV 65
|
||||
#define RE_OP_START_OF_LINE 66
|
||||
#define RE_OP_START_OF_LINE_U 67
|
||||
#define RE_OP_START_OF_STRING 68
|
||||
#define RE_OP_START_OF_WORD 69
|
||||
#define RE_OP_STRING 70
|
||||
#define RE_OP_STRING_FLD 71
|
||||
#define RE_OP_STRING_FLD_REV 72
|
||||
#define RE_OP_STRING_IGN 73
|
||||
#define RE_OP_STRING_IGN_REV 74
|
||||
#define RE_OP_STRING_REV 75
|
||||
#define RE_OP_STRING_SET 76
|
||||
#define RE_OP_STRING_SET_FLD 77
|
||||
#define RE_OP_STRING_SET_FLD_REV 78
|
||||
#define RE_OP_STRING_SET_IGN 79
|
||||
#define RE_OP_STRING_SET_IGN_REV 80
|
||||
#define RE_OP_STRING_SET_REV 81
|
||||
#define RE_OP_BODY_END 82
|
||||
#define RE_OP_BODY_START 83
|
||||
#define RE_OP_END_FUZZY 84
|
||||
#define RE_OP_END_GREEDY_REPEAT 85
|
||||
#define RE_OP_END_GROUP 86
|
||||
#define RE_OP_END_LAZY_REPEAT 87
|
||||
#define RE_OP_GREEDY_REPEAT_ONE 88
|
||||
#define RE_OP_GROUP_RETURN 89
|
||||
#define RE_OP_LAZY_REPEAT_ONE 90
|
||||
#define RE_OP_MATCH_BODY 91
|
||||
#define RE_OP_MATCH_TAIL 92
|
||||
#define RE_OP_START_GROUP 93
|
||||
|
||||
char* re_op_text[] = {
|
||||
"RE_OP_FAILURE",
|
||||
"RE_OP_SUCCESS",
|
||||
"RE_OP_ANY",
|
||||
"RE_OP_ANY_ALL",
|
||||
"RE_OP_ANY_ALL_REV",
|
||||
"RE_OP_ANY_REV",
|
||||
"RE_OP_ANY_U",
|
||||
"RE_OP_ANY_U_REV",
|
||||
"RE_OP_ATOMIC",
|
||||
"RE_OP_BOUNDARY",
|
||||
"RE_OP_BRANCH",
|
||||
"RE_OP_CALL_REF",
|
||||
"RE_OP_CHARACTER",
|
||||
"RE_OP_CHARACTER_IGN",
|
||||
"RE_OP_CHARACTER_IGN_REV",
|
||||
"RE_OP_CHARACTER_REV",
|
||||
"RE_OP_DEFAULT_BOUNDARY",
|
||||
"RE_OP_DEFAULT_END_OF_WORD",
|
||||
"RE_OP_DEFAULT_START_OF_WORD",
|
||||
"RE_OP_END",
|
||||
"RE_OP_END_OF_LINE",
|
||||
"RE_OP_END_OF_LINE_U",
|
||||
"RE_OP_END_OF_STRING",
|
||||
"RE_OP_END_OF_STRING_LINE",
|
||||
"RE_OP_END_OF_STRING_LINE_U",
|
||||
"RE_OP_END_OF_WORD",
|
||||
"RE_OP_FUZZY",
|
||||
"RE_OP_GRAPHEME_BOUNDARY",
|
||||
"RE_OP_GREEDY_REPEAT",
|
||||
"RE_OP_GROUP",
|
||||
"RE_OP_GROUP_CALL",
|
||||
"RE_OP_GROUP_EXISTS",
|
||||
"RE_OP_LAZY_REPEAT",
|
||||
"RE_OP_LOOKAROUND",
|
||||
"RE_OP_NEXT",
|
||||
"RE_OP_PROPERTY",
|
||||
"RE_OP_PROPERTY_IGN",
|
||||
"RE_OP_PROPERTY_IGN_REV",
|
||||
"RE_OP_PROPERTY_REV",
|
||||
"RE_OP_RANGE",
|
||||
"RE_OP_RANGE_IGN",
|
||||
"RE_OP_RANGE_IGN_REV",
|
||||
"RE_OP_RANGE_REV",
|
||||
"RE_OP_REF_GROUP",
|
||||
"RE_OP_REF_GROUP_FLD",
|
||||
"RE_OP_REF_GROUP_FLD_REV",
|
||||
"RE_OP_REF_GROUP_IGN",
|
||||
"RE_OP_REF_GROUP_IGN_REV",
|
||||
"RE_OP_REF_GROUP_REV",
|
||||
"RE_OP_SEARCH_ANCHOR",
|
||||
"RE_OP_SET_DIFF",
|
||||
"RE_OP_SET_DIFF_IGN",
|
||||
"RE_OP_SET_DIFF_IGN_REV",
|
||||
"RE_OP_SET_DIFF_REV",
|
||||
"RE_OP_SET_INTER",
|
||||
"RE_OP_SET_INTER_IGN",
|
||||
"RE_OP_SET_INTER_IGN_REV",
|
||||
"RE_OP_SET_INTER_REV",
|
||||
"RE_OP_SET_SYM_DIFF",
|
||||
"RE_OP_SET_SYM_DIFF_IGN",
|
||||
"RE_OP_SET_SYM_DIFF_IGN_REV",
|
||||
"RE_OP_SET_SYM_DIFF_REV",
|
||||
"RE_OP_SET_UNION",
|
||||
"RE_OP_SET_UNION_IGN",
|
||||
"RE_OP_SET_UNION_IGN_REV",
|
||||
"RE_OP_SET_UNION_REV",
|
||||
"RE_OP_START_OF_LINE",
|
||||
"RE_OP_START_OF_LINE_U",
|
||||
"RE_OP_START_OF_STRING",
|
||||
"RE_OP_START_OF_WORD",
|
||||
"RE_OP_STRING",
|
||||
"RE_OP_STRING_FLD",
|
||||
"RE_OP_STRING_FLD_REV",
|
||||
"RE_OP_STRING_IGN",
|
||||
"RE_OP_STRING_IGN_REV",
|
||||
"RE_OP_STRING_REV",
|
||||
"RE_OP_STRING_SET",
|
||||
"RE_OP_STRING_SET_FLD",
|
||||
"RE_OP_STRING_SET_FLD_REV",
|
||||
"RE_OP_STRING_SET_IGN",
|
||||
"RE_OP_STRING_SET_IGN_REV",
|
||||
"RE_OP_STRING_SET_REV",
|
||||
"RE_OP_BODY_END",
|
||||
"RE_OP_BODY_START",
|
||||
"RE_OP_END_FUZZY",
|
||||
"RE_OP_END_GREEDY_REPEAT",
|
||||
"RE_OP_END_GROUP",
|
||||
"RE_OP_END_LAZY_REPEAT",
|
||||
"RE_OP_GREEDY_REPEAT_ONE",
|
||||
"RE_OP_GROUP_RETURN",
|
||||
"RE_OP_LAZY_REPEAT_ONE",
|
||||
"RE_OP_MATCH_BODY",
|
||||
"RE_OP_MATCH_TAIL",
|
||||
"RE_OP_START_GROUP",
|
||||
};
|
||||
|
||||
#define RE_FLAG_ASCII 0x80
|
||||
#define RE_FLAG_BESTMATCH 0x1000
|
||||
#define RE_FLAG_DEBUG 0x200
|
||||
#define RE_FLAG_DOTALL 0x10
|
||||
#define RE_FLAG_ENHANCEMATCH 0x8000
|
||||
#define RE_FLAG_FULLCASE 0x4000
|
||||
#define RE_FLAG_IGNORECASE 0x2
|
||||
#define RE_FLAG_LOCALE 0x4
|
||||
#define RE_FLAG_MULTILINE 0x8
|
||||
#define RE_FLAG_REVERSE 0x400
|
||||
#define RE_FLAG_TEMPLATE 0x1
|
||||
#define RE_FLAG_UNICODE 0x20
|
||||
#define RE_FLAG_VERBOSE 0x40
|
||||
#define RE_FLAG_VERSION0 0x2000
|
||||
#define RE_FLAG_VERSION1 0x100
|
||||
#define RE_FLAG_WORD 0x800
|
||||
4004
src/regex/_regex_core.py
Normal file
4004
src/regex/_regex_core.py
Normal file
File diff suppressed because it is too large
Load Diff
11997
src/regex/_regex_unicode.c
Normal file
11997
src/regex/_regex_unicode.c
Normal file
File diff suppressed because it is too large
Load Diff
220
src/regex/_regex_unicode.h
Normal file
220
src/regex/_regex_unicode.h
Normal file
@ -0,0 +1,220 @@
|
||||
typedef unsigned char RE_UINT8;
|
||||
typedef signed char RE_INT8;
|
||||
typedef unsigned short RE_UINT16;
|
||||
typedef signed short RE_INT16;
|
||||
typedef unsigned int RE_UINT32;
|
||||
typedef signed int RE_INT32;
|
||||
|
||||
typedef unsigned char BOOL;
|
||||
enum {FALSE, TRUE};
|
||||
|
||||
#define RE_ASCII_MAX 0x7F
|
||||
#define RE_LOCALE_MAX 0xFF
|
||||
#define RE_UNICODE_MAX 0x10FFFF
|
||||
|
||||
#define RE_MAX_CASES 4
|
||||
#define RE_MAX_FOLDED 3
|
||||
|
||||
typedef struct RE_Property {
|
||||
RE_UINT16 name;
|
||||
RE_UINT8 id;
|
||||
RE_UINT8 value_set;
|
||||
} RE_Property;
|
||||
|
||||
typedef struct RE_PropertyValue {
|
||||
RE_UINT16 name;
|
||||
RE_UINT8 value_set;
|
||||
RE_UINT8 id;
|
||||
} RE_PropertyValue;
|
||||
|
||||
typedef RE_UINT32 (*RE_GetPropertyFunc)(RE_UINT32 ch);
|
||||
|
||||
#define RE_PROP_GC 0x0
|
||||
#define RE_PROP_CASED 0xA
|
||||
#define RE_PROP_UPPERCASE 0x9
|
||||
#define RE_PROP_LOWERCASE 0x8
|
||||
|
||||
#define RE_PROP_C 30
|
||||
#define RE_PROP_L 31
|
||||
#define RE_PROP_M 32
|
||||
#define RE_PROP_N 33
|
||||
#define RE_PROP_P 34
|
||||
#define RE_PROP_S 35
|
||||
#define RE_PROP_Z 36
|
||||
|
||||
#define RE_PROP_CN 0
|
||||
#define RE_PROP_LU 1
|
||||
#define RE_PROP_LL 2
|
||||
#define RE_PROP_LT 3
|
||||
#define RE_PROP_LM 4
|
||||
#define RE_PROP_LO 5
|
||||
#define RE_PROP_MN 6
|
||||
#define RE_PROP_ME 7
|
||||
#define RE_PROP_MC 8
|
||||
#define RE_PROP_ND 9
|
||||
#define RE_PROP_NL 10
|
||||
#define RE_PROP_NO 11
|
||||
#define RE_PROP_ZS 12
|
||||
#define RE_PROP_ZL 13
|
||||
#define RE_PROP_ZP 14
|
||||
#define RE_PROP_CC 15
|
||||
#define RE_PROP_CF 16
|
||||
#define RE_PROP_CO 17
|
||||
#define RE_PROP_CS 18
|
||||
#define RE_PROP_PD 19
|
||||
#define RE_PROP_PS 20
|
||||
#define RE_PROP_PE 21
|
||||
#define RE_PROP_PC 22
|
||||
#define RE_PROP_PO 23
|
||||
#define RE_PROP_SM 24
|
||||
#define RE_PROP_SC 25
|
||||
#define RE_PROP_SK 26
|
||||
#define RE_PROP_SO 27
|
||||
#define RE_PROP_PI 28
|
||||
#define RE_PROP_PF 29
|
||||
|
||||
#define RE_PROP_C_MASK 0x00078001
|
||||
#define RE_PROP_L_MASK 0x0000003E
|
||||
#define RE_PROP_M_MASK 0x000001C0
|
||||
#define RE_PROP_N_MASK 0x00000E00
|
||||
#define RE_PROP_P_MASK 0x30F80000
|
||||
#define RE_PROP_S_MASK 0x0F000000
|
||||
#define RE_PROP_Z_MASK 0x00007000
|
||||
|
||||
#define RE_PROP_ALNUM 0x460001
|
||||
#define RE_PROP_ALPHA 0x070001
|
||||
#define RE_PROP_ANY 0x470001
|
||||
#define RE_PROP_ASCII 0x480001
|
||||
#define RE_PROP_ASSIGNED 0x490001
|
||||
#define RE_PROP_BLANK 0x4A0001
|
||||
#define RE_PROP_CNTRL 0x00000F
|
||||
#define RE_PROP_DIGIT 0x000009
|
||||
#define RE_PROP_GRAPH 0x4B0001
|
||||
#define RE_PROP_LOWER 0x080001
|
||||
#define RE_PROP_PRINT 0x4C0001
|
||||
#define RE_PROP_PUNCT 0x000022
|
||||
#define RE_PROP_SPACE 0x190001
|
||||
#define RE_PROP_UPPER 0x090001
|
||||
#define RE_PROP_WORD 0x4D0001
|
||||
#define RE_PROP_XDIGIT 0x4E0001
|
||||
|
||||
#define RE_BREAK_OTHER 0
|
||||
#define RE_BREAK_DOUBLEQUOTE 1
|
||||
#define RE_BREAK_SINGLEQUOTE 2
|
||||
#define RE_BREAK_HEBREWLETTER 3
|
||||
#define RE_BREAK_CR 4
|
||||
#define RE_BREAK_LF 5
|
||||
#define RE_BREAK_NEWLINE 6
|
||||
#define RE_BREAK_EXTEND 7
|
||||
#define RE_BREAK_REGIONALINDICATOR 8
|
||||
#define RE_BREAK_FORMAT 9
|
||||
#define RE_BREAK_KATAKANA 10
|
||||
#define RE_BREAK_ALETTER 11
|
||||
#define RE_BREAK_MIDLETTER 12
|
||||
#define RE_BREAK_MIDNUM 13
|
||||
#define RE_BREAK_MIDNUMLET 14
|
||||
#define RE_BREAK_NUMERIC 15
|
||||
#define RE_BREAK_EXTENDNUMLET 16
|
||||
|
||||
#define RE_GBREAK_OTHER 0
|
||||
#define RE_GBREAK_CR 1
|
||||
#define RE_GBREAK_LF 2
|
||||
#define RE_GBREAK_CONTROL 3
|
||||
#define RE_GBREAK_EXTEND 4
|
||||
#define RE_GBREAK_REGIONALINDICATOR 5
|
||||
#define RE_GBREAK_SPACINGMARK 6
|
||||
#define RE_GBREAK_L 7
|
||||
#define RE_GBREAK_V 8
|
||||
#define RE_GBREAK_T 9
|
||||
#define RE_GBREAK_LV 10
|
||||
#define RE_GBREAK_LVT 11
|
||||
#define RE_GBREAK_PREPEND 12
|
||||
|
||||
extern char* re_strings[1155];
|
||||
extern RE_Property re_properties[145];
|
||||
extern RE_PropertyValue re_property_values[1244];
|
||||
extern RE_UINT16 re_expand_on_folding[104];
|
||||
extern RE_GetPropertyFunc re_get_property[79];
|
||||
|
||||
RE_UINT32 re_get_general_category(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_block(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_script(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_word_break(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_grapheme_cluster_break(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_sentence_break(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_math(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_alphabetic(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_lowercase(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_uppercase(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_cased(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_case_ignorable(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_changes_when_lowercased(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_changes_when_uppercased(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_changes_when_titlecased(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_changes_when_casefolded(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_changes_when_casemapped(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_id_start(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_id_continue(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_xid_start(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_xid_continue(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_default_ignorable_code_point(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_grapheme_extend(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_grapheme_base(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_grapheme_link(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_white_space(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_bidi_control(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_join_control(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_dash(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_hyphen(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_quotation_mark(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_terminal_punctuation(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_other_math(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_hex_digit(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_ascii_hex_digit(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_other_alphabetic(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_ideographic(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_diacritic(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_extender(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_other_lowercase(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_other_uppercase(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_noncharacter_code_point(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_other_grapheme_extend(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_ids_binary_operator(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_ids_trinary_operator(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_radical(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_unified_ideograph(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_other_default_ignorable_code_point(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_deprecated(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_soft_dotted(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_logical_order_exception(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_other_id_start(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_other_id_continue(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_sterm(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_variation_selector(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_pattern_white_space(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_pattern_syntax(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_hangul_syllable_type(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_bidi_class(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_canonical_combining_class(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_decomposition_type(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_east_asian_width(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_joining_group(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_joining_type(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_line_break(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_numeric_type(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_numeric_value(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_bidi_mirrored(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_indic_matra_category(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_indic_syllabic_category(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_alphanumeric(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_any(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_ascii(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_assigned(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_blank(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_graph(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_print(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_word(RE_UINT32 ch);
|
||||
RE_UINT32 re_get_xdigit(RE_UINT32 ch);
|
||||
int re_get_all_cases(RE_UINT32 ch, RE_UINT32* codepoints);
|
||||
RE_UINT32 re_get_simple_case_folding(RE_UINT32 ch);
|
||||
int re_get_full_case_folding(RE_UINT32 ch, RE_UINT32* codepoints);
|
||||
Loading…
x
Reference in New Issue
Block a user